Paper Digest: Recent Papers on Question Answering
Paper Digest Team extracted all recent Question Answering related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic.
For users searching for papers/patents/grants with highlights, related papers, patents, grants, experts and organizations, please try our search console. We also provide an exclusive professor search service to find more than 400K professors across the US using their research work.
If you do not want to miss any interesting academic paper, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Question Answering
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | Extending Sticky-Datalog+/- Via Finite-Position SelectionFunctions: Tractability, Algorithms, and Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a bottom-up QA algorithm for programs in the class sch(S), for a general selection S.As a particular case, we obtain a polynomial-time QA algorithm for JWS and weakly-sticky programs. |
Leopoldo Bertossi; Mostafa Milani; | arxiv-cs.DB | 2021-08-02 |
| 2 | MuSiQue: Multi-hop Questions Via Single-hop Question Composition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To build challenging multi-hop question answering datasets, we propose a bottom-up semi-automatic process of constructing multi-hop question via composition of single-hop questions. We also build an even more challenging dataset, MuSiQue-Full, consisting of answerable and unanswerable contrast question pairs, where model performance drops further by 13+ F1 pts. |
Harsh Trivedi; Niranjan Balasubramanian; Tushar Khot; Ashish Sabharwal; | arxiv-cs.CL | 2021-08-01 |
| 3 | Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle more complex questions, we aim at creating knowledge base from clinical notes to link different patients and clinical notes, and performing knowledge base question answering (KBQA). Based on the expert annotations in n2c2, we first created the ClinicalKBQA dataset that includes 8,952 QA pairs and covers questions about seven medical topics through 322 question templates. |
Ping Wang; Tian Shi; Khushbu Agarwal; Sutanay Choudhury; Chandan K. Reddy; | arxiv-cs.CL | 2021-08-01 |
| 4 | Automatic Claim Review for Climate Science Via Explanation Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we try to aid them by automating generating explanation for a predicted veracity label for a claim by deploying the approach used in open domain question answering of a fusion in decoder augmented with retrieved supporting passages from an external knowledge. |
Shraey Bhatia; Jey Han Lau; Timothy Baldwin; | arxiv-cs.CL | 2021-07-30 |
| 5 | Talk2Data: High-Level Question Decomposition for Data-Oriented Question and Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the issue, in this paper, we introduce Talk2Data, a data-oriented online question and answering system that supports answering both low-level and high-level questions. |
DANQING SHI et. al. | arxiv-cs.HC | 2021-07-29 |
| 6 | An Online Question Answering System Based on Sub-graph Searching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this pa-per, we design a sub-graph searching mechanism to solve this problem by creating sub-graph index, and each answer generation step is restricted in the sub-graph level. |
Shuangyong Song; | arxiv-cs.AI | 2021-07-28 |
| 7 | Greedy Gradient Ensemble for Robust Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information. |
Xinzhe Han; Shuhui Wang; Chi Su; Qingming Huang; Qi Tian; | arxiv-cs.CV | 2021-07-27 |
| 8 | QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The study is aimed at both practitioners looking for pointers to the wealth of existing data, and at researchers working on new resources. |
Anna Rogers; Matt Gardner; Isabelle Augenstein; | arxiv-cs.CL | 2021-07-27 |
| 9 | A Semantic-based Method for Unsupervised Commonsense Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel SEmantic-based Question Answering method (SEQA) for unsupervised commonsense question answering. |
YILIN NIU et. al. | acl | 2021-07-26 |
| 10 | Continuous Language Generative Flow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a flow-based language generation model by adapting previous flow generative models to language generation via continuous input embeddings, adapted affine coupling structures, and a novel architecture for autoregressive text generation. |
Zineng Tang; Shiyue Zhang; Hyounghun Kim; Mohit Bansal; | acl | 2021-07-26 |
| 11 | Neural Semi-Markov CRF for Monolingual Word Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel neural semi-Markov CRF alignment model, which unifies word and phrase alignments through variable-length spans. |
Wuwei Lan; Chao Jiang; Wei Xu; | acl | 2021-07-26 |
| 12 | Towards Visual Question Answering on Pathology Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to develop a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images. |
XUEHAI HE et. al. | acl | 2021-07-26 |
| 13 | A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple transformer-based neural model for relation linking that leverages the AMR semantic parse of a sentence. |
TAHIRA NASEEM et. al. | acl | 2021-07-26 |
| 14 | Improving Pretrained Cross-Lingual Language Models Via Self-Labeled Word Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task. |
ZEWEN CHI et. al. | acl | 2021-07-26 |
| 15 | Mind Your Outliers! Investigating The Negative Impact of Outliers on Active Learning for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand this discrepancy, we profile 8 active learning methods on a per-example basis, and identify the problem as collective outliers – groups of examples that active learning methods prefer to acquire but models fail to learn (e.g., questions that ask about text in images or require external knowledge). |
Siddharth Karamcheti; Ranjay Krishna; Li Fei-Fei; Christopher Manning; | acl | 2021-07-26 |
| 16 | Guiding The Growth: Difficulty-Controllable Question Generation Through Step-by-Step Rewriting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain. |
YI CHENG et. al. | acl | 2021-07-26 |
| 17 | StructuralLM: Structural Pre-training for Form Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new pre-training approach, StructuralLM, to jointly leverage cell and layout information from scanned documents. |
CHENLIANG LI et. al. | acl | 2021-07-26 |
| 18 | DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce DESCGEN: given mentions spread over multiple documents, the goal is to generate an entity summary description. |
Weijia Shi; Mandar Joshi; Luke Zettlemoyer; | acl | 2021-07-26 |
| 19 | ReadOnce Transformers: Reusable Representations of Text for Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ReadOnce Transformers, an approach to convert a transformer-based model into one that can build an information-capturing, task-independent, and compressed representation of text. |
Shih-Ting Lin; Ashish Sabharwal; Tushar Khot; | acl | 2021-07-26 |
| 20 | Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework for computationally measuring uptake, by (1) releasing a dataset of student-teacher exchanges extracted from US math classroom transcripts annotated for uptake by experts; (2) formalizing uptake as pointwise Jensen-Shannon Divergence (pJSD), estimated via next utterance classification; (3) conducting a linguistically-motivated comparison of different unsupervised measures and (4) correlating these measures with educational outcomes. |
DOROTTYA DEMSZKY et. al. | acl | 2021-07-26 |
| 21 | CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a two-stage Collective Relation Integration (CoRI) model, where the first stage independently makes candidate predictions, and the second stage employs a collective model that accesses all candidate predictions to make globally coherent predictions. |
Zhengbao Jiang; Jialong Han; Bunyamin Sisman; Xin Luna Dong; | acl | 2021-07-26 |
| 22 | Consistency Regularization for Cross-Lingual Fine-Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. |
BO ZHENG et. al. | acl | 2021-07-26 |
| 23 | Pre-training Universal Language Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces universal language representation learning, i.e., embeddings of different levels of linguistic units or text with quite diverse lengths in a uniform vector space. |
Yian Li; Hai Zhao; | acl | 2021-07-26 |
| 24 | Recursive Tree-Structured Self-Attention for Answer Sentence Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the Tree Aggregation Transformer: a novel recursive, tree-structured self-attention model for AS2. |
Khalil Mrini; Emilia Farcas; Ndapa Nakashole; | acl | 2021-07-26 |
| 25 | XMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new contrastive learning method called Cross Momentum Contrastive learning (xMoCo), for learning a dual-encoder model for question-passage matching. |
Nan Yang; Furu Wei; Binxing Jiao; Daxing Jiang; Linjun Yang; | acl | 2021-07-26 |
| 26 | Zero-shot Event Extraction Via Transfer Learning: Challenges and Insights Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore the possibility of zero-shot event extraction by formulating it as a set of Textual Entailment (TE) and/or Question Answering (QA) queries (e.g. A city was attacked entails There is an attack), exploiting pretrained TE/QA models for direct transfer. |
Qing Lyu; Hongming Zhang; Elior Sulem; Dan Roth; | acl | 2021-07-26 |
| 27 | Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using these augmentations, we propose a new robustness measure, Robustness to Augmented Data (RAD), which measures the consistency of model predictions between original and augmented examples. |
Daniel Rosenberg; Itai Gat; Amir Feder; Roi Reichart; | acl | 2021-07-26 |
| 28 | Few-Shot Question Answering By Pretraining Span Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new pretraining scheme tailored for question answering: recurring span selection. |
Ori Ram; Yuval Kirstain; Jonathan Berant; Amir Globerson; Omer Levy; | acl | 2021-07-26 |
| 29 | ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models Via Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel contrastive learning framework ERICA to obtain a deep understanding of the entities and their relations in text. |
YUJIA QIN et. al. | acl | 2021-07-26 |
| 30 | Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to model these implied entities, which we refer to as the focal entities of the conversation. |
Yunshi Lan; Jing Jiang; | acl | 2021-07-26 |
| 31 | Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a hybrid framework that takes both textual and tabular evidences as input and generates either direct answers or SQL queries depending on which form could better answer the question. |
ALEXANDER HANBO LI et. al. | acl | 2021-07-26 |
| 32 | VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. |
FULI LUO et. al. | acl | 2021-07-26 |
| 33 | A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, we propose a novel Multi-Task Learning (MTL) method with data augmentation for medical question understanding. |
KHALIL MRINI et. al. | acl | 2021-07-26 |
| 34 | Coreference Reasoning in Machine Reading Comprehension Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a methodology for creating MRC datasets that better reflect the challenges of coreference reasoning and use it to create a sample evaluation set. |
Mingzhu Wu; Nafise Sadat Moosavi; Dan Roth; Iryna Gurevych; | acl | 2021-07-26 |
| 35 | ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To showcase the usefulness of this task formulation, we introduce ForecastQA, a question-answering dataset consisting of 10,392 event forecasting questions, which have been collected and verified via crowdsourcing efforts. |
WOOJEONG JIN et. al. | acl | 2021-07-26 |
| 36 | A Mutual Information Maximization Approach for The Spurious Solution Problem in Weakly Supervised Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to alleviate the spurious solution problem, we propose to explicitly exploit such semantic correlations by maximizing the mutual information between question-answer pairs and predicted solutions. |
Zhihong Shao; Lifeng Shang; Qun Liu; Minlie Huang; | acl | 2021-07-26 |
| 37 | Challenges in Information-Seeking QA: Unanswerable Questions and Paragraph Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our controlled experiments suggest two headrooms – paragraph selection and answerability prediction, i.e. whether the paired evidence document contains the answer to the query or not. |
Akari Asai; Eunsol Choi; | acl | 2021-07-26 |
| 38 | Generation-Augmented Retrieval for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Generation-Augmented Retrieval (GAR) for answering open-domain questions, which augments a query through text generation of heuristically discovered relevant contexts without external resources as supervision. |
YUNING MAO et. al. | acl | 2021-07-26 |
| 39 | LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we take a different, neuro-symbolic approach that combines the advantages of using interpretable rules based on first-order logic with the performance of neural learning. |
HANG JIANG et. al. | acl | 2021-07-26 |
| 40 | Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend PoWER-BERT (Goyal et al., 2020) and propose Length-Adaptive Transformer that can be used for various inference scenarios after one-shot training. |
Gyuwan Kim; Kyunghyun Cho; | acl | 2021-07-26 |
| 41 | Towards More Equitable Question Answering Systems: How Much More Data Do You Need? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this project we take a step back and study which approaches allow us to take the most advantage of existing resources in order to produce QA systems in many languages. |
Arnab Debnath; Navid Rajabi; Fardina Fathmiul Alam; Antonios Anastasopoulos; | acl | 2021-07-26 |
| 42 | Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Adaptive Passage Encoder, an AC method that can be applied to an existing ODQA model and can be trained efficiently on a single GPU. |
Yuxiang Wu; Pasquale Minervini; Pontus Stenetorp; Sebastian Riedel; | acl | 2021-07-26 |
| 43 | GTM: A Generative Triple-wise Model for Conversational Question Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these problems, we propose a generative triple-wise model with hierarchical variations for open-domain conversational question generation (CQG). |
Lei Shen; Fandong Meng; Jinchao Zhang; Yang Feng; Jie Zhou; | acl | 2021-07-26 |
| 44 | Towards A More Robust Evaluation for Conversational Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we highlight this effect and propose new tools for evaluation and training in order to guard against the noted issues. |
Wissam Siblini; Baris Sayil; Yacine Kessaci; | acl | 2021-07-26 |
| 45 | End-to-End Training of Neural Retrievers for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we systematically study retriever pre-training. |
DEVENDRA SACHAN et. al. | acl | 2021-07-26 |
| 46 | UnitedQA: A Hybrid Approach for Open Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for leveraging the strengths of both models. |
HAO CHENG et. al. | acl | 2021-07-26 |
| 47 | Efficient Passage Retrieval with Hashing for Open-domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Binary Passage Retriever (BPR), a memory-efficient neural retrieval model that integrates a learning-to-hash technique into the state-of-the-art Dense Passage Retriever (DPR) to represent the passage index using compact binary codes rather than continuous vectors. |
Ikuya Yamada; Akari Asai; Hannaneh Hajishirzi; | acl | 2021-07-26 |
| 48 | What Ingredients Make for An Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we compare the efficacy of interventions that have been proposed in prior work as ways of improving data quality. |
NIKITA NANGIA et. al. | acl | 2021-07-26 |
| 49 | Learning Faithful Representations of Causal Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we define the faithfulness property of contextual embeddings to capture geometric distance-based properties of directed acyclic causal graphs. |
Ananth Balashankar; Lakshminarayanan Subramanian; | acl | 2021-07-26 |
| 50 | Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a supervised data mining method using an accurate early fusion model to improve the training of an efficient late fusion retrieval model. |
Yinfei Yang; Ning Jin; Kuo Lin; Mandy Guo; Daniel Cer; | acl | 2021-07-26 |
| 51 | Learning Event Graph Knowledge for Abductive Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this gap, we propose a variational autoencoder based model ege-RoBERTa, which employs a latent variable to capture the necessary commonsense knowledge from event graph for guiding the abductive reasoning task. |
Li Du; Xiao Ding; Ting Liu; Bing Qin; | acl | 2021-07-26 |
| 52 | Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Motion-Appearance Synergistic Networks (MASN), which embed two cross-modal features grounded on motion and appearance information and selectively utilize them depending on the question’s intentions. |
Ahjeong Seo; Gi-Cheon Kang; Joonhan Park; Byoung-Tak Zhang; | acl | 2021-07-26 |
| 53 | Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework, ExCorD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. |
Gangwoo Kim; Hyunjae Kim; Jungsoo Park; Jaewoo Kang; | acl | 2021-07-26 |
| 54 | TAT-QA: A Question Answering Benchmark on A Hybrid of Tabular and Textual Content in Finance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions. |
FENGBIN ZHU et. al. | acl | 2021-07-26 |
| 55 | Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a reinforcement learning-based framework for abstractive question summarization. |
Shweta Yadav; Deepak Gupta; Asma Ben Abacha; Dina Demner-Fushman; | acl | 2021-07-26 |
| 56 | On The Efficacy of Adversarial Data Collection for Question Answering: Results from A Large-Scale Randomized Study Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct a large-scale controlled study focused on question answering, assigning workers at random to compose questions either (i) adversarially (with a model in the loop); or (ii) in the standard fashion (without a model). |
Divyansh Kaushik; Douwe Kiela; Zachary C. Lipton; Wen-tau Yih; | acl | 2021-07-26 |
| 57 | QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their values, given utterances from new domains without training on the target domain. |
XINYA DU et. al. | acl | 2021-07-26 |
| 58 | In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new method to enhance the reasoning capabilities of a multi-modal pretrained model (Vision+Language BERT) by integrating facts extracted from an external knowledge base. |
Peter Vickers; Nikolaos Aletras; Emilio Monti; Lo?c Barrault; | acl | 2021-07-26 |
| 59 | One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present CORA, a Cross-lingual Open-Retrieval Answer Generation model that can answer questions across many languages even when language-specific annotated data or knowledge sources are unavailable. |
Akari Asai; Xinyan Yu; Jungo Kasai; Hannaneh Hajishirzi; | arxiv-cs.CL | 2021-07-26 |
| 60 | KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine the challenges that still prevent these techniques from practical deployment. |
Chia-Hsuan Lee; Oleksandr Polozov; Matthew Richardson; | acl | 2021-07-26 |
| 61 | Can Generative Pre-trained Language Models Serve As Knowledge Bases for Closed-book QA? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We construct a new dataset of closed-book QA using SQuAD, and investigate the performance of BART. |
Cunxiang Wang; Pai Liu; Yue Zhang; | acl | 2021-07-26 |
| 62 | CoSQA: 20,000+ Web Queries for Code Search and Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To remedy this, we introduce CoSQA dataset. It includes 20,604 labels for pairs of natural language queries and codes, each annotated by at least 3 human annotators. |
JUNJIE HUANG et. al. | acl | 2021-07-26 |
| 63 | A Neural Model for Joint Document and Snippet Ranking in Question Answering for Large Document Collections Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an architecture for joint document and snippet ranking, the two middle stages, which leverages the intuition that relevant documents have good snippets and good snippets come from relevant documents. |
Dimitris Pappas; Ion Androutsopoulos; | acl | 2021-07-26 |
| 64 | BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Of course, we do not have answers now, but, as an attempt to find better neural architectures and training schemes, we pretrain a simple CNN using a GAN-style learning scheme and Wikipedia data, and then integrate it with standard TLMs. |
Jong-Hoon Oh; Ryu Iida; Julien Kloetzer; Kentaro Torisawa; | acl | 2021-07-26 |
| 65 | Explanations for CommonsenseQA: New Dataset and Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our explanation definition is based on certain desiderata, and translates an explanation into a set of positive and negative common-sense properties (aka facts) which not only explain the correct answer choice but also refute the incorrect ones. |
SHOURYA AGGARWAL et. al. | acl | 2021-07-26 |
| 66 | Privacy at Scale: Introducing The PrivaSeer Corpus of Web Privacy Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe a corpus creation pipeline with stages that include a web crawler, language detection, document classification, duplicate and near-duplicate removal, and content extraction. |
Mukund Srinath; Shomir Wilson; C Lee Giles; | acl | 2021-07-26 |
| 67 | Learning to Perturb Word Embeddings for Out-of-distribution QA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we propose a simple yet effective DA method based on a stochastic noise generator, which learns to perturb the word embedding of the input questions and context without changing their semantics. |
Seanie Lee; Minki Kang; Juho Lee; Sung Ju Hwang; | acl | 2021-07-26 |
| 68 | Which Linguist Invented The Lightbulb? Presupposition Verification for Question-Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Through a user preference study, we demonstrate that the oracle behavior of our proposed system-which provides responses based on presupposition failure-is preferred over the oracle behavior of existing QA systems. Then, we present a novel framework for implementing such a system in three steps: presupposition generation, presupposition verification, and explanation generation, reporting progress on each. |
Najoung Kim; Ellie Pavlick; Burcu Karagol Ayan; Deepak Ramachandran; | acl | 2021-07-26 |
| 69 | COSY: COunterfactual SYntax for Cross-Lingual Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We tackle this issue by incorporating language-agnostic information, specifically, universal syntax such as dependency relations and POS tags, into language models, based on the observation that universal syntax is transferable across different languages. |
Sicheng Yu; Hao Zhang; Yulei Niu; Qianru Sun; Jing Jiang; | acl | 2021-07-26 |
| 70 | An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To avoid the disadvantages of existing models and exploit the generalized representation across the two tasks, we design an end-to-end progressive multi-task learning model for jointly modeling medical NER and NEN in an effective way. |
Baohang Zhou; Xiangrui Cai; Ying Zhang; Xiaojie Yuan; | acl | 2021-07-26 |
| 71 | Syntax-Enhanced Pre-trained Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. |
ZENAN XU et. al. | acl | 2021-07-26 |
| 72 | Improving Document Representations By Generating Pseudo Query Embeddings for Dense Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we design a method to mimic the queries to each of the documents by an iterative clustering process and represent the documents by multiple pseudo queries (i.e., the cluster centroids). |
HONGYIN TANG et. al. | acl | 2021-07-26 |
| 73 | Multi-Scale Progressive Attention Network for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose a novel Multi-Scale Progressive Attention Network (MSPAN) to achieve relational reasoning between cross-scale video information. |
Zhicheng Guo; Jiaxuan Zhao; Licheng Jiao; Xu Liu; Lingling Li; | acl | 2021-07-26 |
| 74 | Answering Ambiguous Questions Through Generative Evidence Fusion and Round-Trip Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a model that aggregates and combines evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions. |
YIFAN GAO et. al. | acl | 2021-07-26 |
| 75 | Discrete Cosine Transform As Universal Sentence Encoder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we utilize DCT encoder to generate universal sentence representation for different languages such as German, French, Spanish and Russian. |
Nada Almarwani; Mona Diab; | acl | 2021-07-26 |
| 76 | ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this gap, we design annotation protocols motivated by an issues-viewpoints-assertions framework to crowdsource four new datasets on diverse online conversation forms of news comments, discussion forums, community question answering forums, and email threads. |
ALEXANDER FABBRI et. al. | acl | 2021-07-26 |
| 77 | Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address these problems by a novel Rationale-Enriched Answer Generator (REAG), which incorporates an extractive mechanism into a generative model. |
Chenliang Li; Bin Bi; Ming Yan; Wei Wang; Songfang Huang; | acl | 2021-07-26 |
| 78 | Comparing Test Sets with Item Response Theory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To measure this uniformly across datasets, we draw on Item Response Theory and evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples. |
CLARA VANIA et. al. | acl | 2021-07-26 |
| 79 | SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce SMedBERT, a medical PLM trained on large-scale medical corpora, incorporating deep structured semantic knowledge from neighbours of linked-entity. |
TAOLIN ZHANG et. al. | acl | 2021-07-26 |
| 80 | Question Answering Over Temporal Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this challenge by presenting CRONQUESTIONS, the largest known Temporal KGQA dataset, clearly stratified into buckets of structural complexity. |
Apoorv Saxena; Soumen Chakrabarti; Partha Talukdar; | acl | 2021-07-26 |
| 81 | ABCD: A Graph Framework to Convert Complex Sentences to A Covering Set of Simple Sentences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new task to decompose each complex sentence into simple sentences derived from the tensed clauses in the source, and a novel problem formulation as a graph edit task. |
Yanjun Gao; Ting-Hao Huang; Rebecca J. Passonneau; | acl | 2021-07-26 |
| 82 | Learning Dense Representations of Phrases at Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an effective method to learn phrase representations from the supervision of reading comprehension tasks, coupled with novel negative sampling methods. |
Jinhyuk Lee; Mujeen Sung; Jaewoo Kang; Danqi Chen; | acl | 2021-07-26 |
| 83 | Robustifying Multi-hop QA Through Pseudo-Evidentiality Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we propose a new approach to learn evidentiality, deciding whether the answer prediction is supported by correct evidences, without such annotations. |
Kyungjae Lee; Seung-won Hwang; Sang-eun Han; Dohyeon Lee; | acl | 2021-07-26 |
| 84 | Evaluating Entity Disambiguation and The Role of Popularity in Retrieval-Based NLP Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an evaluation benchmark for assessing the entity disambiguation capabilities of these retrievers, which we call Ambiguous Entity Retrieval (AmbER) sets. |
Anthony Chen; Pallavi Gudipati; Shayne Longpre; Xiao Ling; Sameer Singh; | acl | 2021-07-26 |
| 85 | Joint Models for Answer Verification in Question Answering Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies joint models for selecting correct answer sentences among the top k provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. |
Zeyu Zhang; Thuy Vu; Alessandro Moschitti; | acl | 2021-07-26 |
| 86 | Improving Factual Consistency of Abstractive Summarization Via Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present an approach to address factual consistency in summarization. |
FENG NAN et. al. | acl | 2021-07-26 |
| 87 | Syntax-augmented Multilingual BERT for Cross-lingual Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work shows that explicitly providing language syntax and training mBERT using an auxiliary objective to encode the universal dependency tree structure helps cross-lingual transfer. |
Wasi Ahmad; Haoran Li; Kai-Wei Chang; Yashar Mehdad; | acl | 2021-07-26 |
| 88 | ERNIE-Doc: A Retrospective Long-Document Modeling Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ERNIE-Doc, a document-level language pretraining model based on Recurrence Transformers. |
SIYU DING et. al. | acl | 2021-07-26 |
| 89 | Multi-Task Retrieval for Knowledge-Intensive Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Driven by the question of whether a neural retrieval model can be _universal_ and perform robustly on a wide variety of problems, we propose a multi-task trained model. |
JEAN MAILLARD et. al. | acl | 2021-07-26 |
| 90 | Check It Again:Progressive Visual Question Answering Via Visual Entailment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a select-and-rerank (SAR) progressive framework based on Visual Entailment. |
Qingyi Si; Zheng Lin; Ming yu Zheng; Peng Fu; Weiping Wang; | acl | 2021-07-26 |
| 91 | Hybrid Autoregressive Solver for Scalable Abductive Natural Language Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To maximise both accuracy and inference time, we propose a hybrid abductive solver that autoregressively combines a dense bi-encoder with a sparse model of explanatory power, computed leveraging explicit patterns in the explanations. |
Marco Valentino; Mokanarangan Thayaparan; Deborah Ferreira; André Freitas; | arxiv-cs.CL | 2021-07-25 |
| 92 | X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to handle the problem implicitly. |
Jingjing Jiang; Ziyi Liu; Yifan Liu; Zhixiong Nan; Nanning Zheng; | arxiv-cs.CV | 2021-07-24 |
| 93 | The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the use of bilingual intermediate pretraining as a reliable technique to derive large and consistent performance gains on three different NLP tasks using code-switched text. |
Archiki Prasad; Mohammad Ali Rehan; Shreya Pathak; Preethi Jyothi; | arxiv-cs.CL | 2021-07-21 |
| 94 | CogME: A Novel Evaluation Metric for Video Understanding Intelligence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To examine the suitability of a VideoQA dataset for validating video understanding intelligence, we evaluated the baseline model of the DramaQA dataset by applying CogME. |
MINJUNG SHIN et. al. | arxiv-cs.CV | 2021-07-20 |
| 95 | CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the problem of injecting causal knowledge into pre-trained models. |
Zhongyang Li; Xiao Ding; Kuo Liao; Ting Liu; Bing Qin; | arxiv-cs.CL | 2021-07-20 |
| 96 | Separating Skills and Concepts for Novel Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel method for learning to compose skills and concepts that separates these two factors implicitly within a model by learning grounded concept representations and disentangling the encoding of skills from that of concepts. |
Spencer Whitehead; Hui Wu; Heng Ji; Rogerio Feris; Kate Saenko; | arxiv-cs.CV | 2021-07-19 |
| 97 | Bridging The Gap Between Language Model and Reading Comprehension: Unsupervised MRC Via Self-Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new framework for unsupervised MRC. |
NING BIAN et. al. | arxiv-cs.CL | 2021-07-18 |
| 98 | A Discriminative Semantic Ranker for Question Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to tackle the dilemma of the first-stage ranker, and propose a discriminative semantic ranker, namely DenseTrans, for high-recall retrieval. |
YINQIONG CAI et. al. | arxiv-cs.IR | 2021-07-17 |
| 99 | Are Multilingual Models The Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on Catalan with the aim to explore to what extent a medium-sized monolingual language model is competitive with state-of-the-art large multilingual models. For this, we: (1) build a clean, high-quality textual Catalan corpus (CaText), the largest to date (but only a fraction of the usual size of the previous work in monolingual language models), (2) train a Transformer-based language model for Catalan (BERTa), and (3) devise a thorough evaluation in a diversity of settings, comprising a complete array of downstream tasks, namely, Part of Speech Tagging, Named Entity Recognition and Classification, Text Classification, Question Answering, and Semantic Textual Similarity, with most of the corresponding datasets being created ex novo. |
JORDI ARMENGOL-ESTAPÉ et. al. | arxiv-cs.CL | 2021-07-16 |
| 100 | Exploiting Rich Syntax for Better Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous works for encoding questions mainly focus on the word sequences, but seldom consider the information from syntactic trees.In this paper, we propose an approach to learn syntax-based representations for KBQA. |
Pengju Zhang; Yonghui Jia; Muhua Zhu; Wenliang Chen; Min Zhang; | arxiv-cs.CL | 2021-07-16 |
| 101 | A Survey of Knowledge Graph Embedding and Their Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces growth in the field of KG embedding from simple translation-based models to enrichment-based models. |
Shivani Choudhary; Tarun Luthra; Ashima Mittal; Rajat Singh; | arxiv-cs.IR | 2021-07-16 |
| 102 | On The Orthogonality of Bias and Utility in Ad Hoc Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we empirically study this tradeoff and explore whether it would be possible to reduce bias while maintaining similar retrieval utility. |
Amin Bigdeli; Negar Arabzadeh; Shirin Seyedsalehi; Morteza Zihayat; Ebrahim Bagheri; | sigir | 2021-07-13 |
| 103 | Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we identify a key structural idiom in OKVQA ,viz., S3 (select, substitute and search), and build a new data set and challenge around it. |
AMAN JAIN et. al. | sigir | 2021-07-13 |
| 104 | Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Graphhopper, a novel method that approaches the task by integrating knowledge graph reasoning, computer vision, and natural language processing techniques. |
RAJAT KONER et. al. | arxiv-cs.CV | 2021-07-13 |
| 105 | Towards Building A Food Knowledge Graph for Internet of Food Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Scope and approach: We review the evolution of food knowledge organization, from food classification, food ontology to food knowledge graphs. |
Weiqing Min; Chunlin Liu; Shuqiang Jiang; | arxiv-cs.CV | 2021-07-13 |
| 106 | AliMe DA: A Data Augmentation Framework for Question Answering in Cold-start Scenarios Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose AliMe DA, a practical data augmentation (DA) framework that consists of data production, denoising and consumption, to alleviate this problem. |
GUOHAI XU et. al. | sigir | 2021-07-13 |
| 107 | Event Occurrence Date Estimation Based on Multivariate Time Series Analysis Over Temporal Document Collections Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose an approach to temporal profiling of event mentions in text. |
Jiexin Wang; Adam Jatowt; Masatoshi Yoshikawa; | sigir | 2021-07-13 |
| 108 | Synthetic Target Domain Supervision for Open Retrieval QA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we stress-test the Dense Passage Retriever (DPR)—a state-of-the-art (SOTA) open domain neural retrieval model—on closed and specialized target domains such as COVID-19, and find that it lags behind standard BM25 in this important real-world setting. |
REVANTH GANGI REDDY et. al. | sigir | 2021-07-13 |
| 109 | Answering Any-hop Open-domain Questions with Iterative Document Reranking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose a unified QA framework to answer any-hop open-domain questions, which iteratively retrieves, reranks and filters documents, and adaptively determines when to stop the retrieval process. |
Yuyu Zhang; Ping Nie; Arun Ramamurthy; Le Song; | sigir | 2021-07-13 |
| 110 | LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel Language-Prior Feedback (LPF) objective function, to re-balance the proportion of each answer’s loss value in the total VQA loss. |
Zujie Liang; Haifeng Hu; Jiaying Zhu; | sigir | 2021-07-13 |
| 111 | Learning Discriminative Neural Representations for Event Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the challenge, we propose to learn discriminative neural representations (DNR) from texts. |
Jinzhi Liao; Xiang Zhao; Xinyi Li; Lingling Zhang; Jiuyang Tang; | sigir | 2021-07-13 |
| 112 | Passage Retrieval for Outside-Knowledge Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address multi-modal information needs that contain text questions and images by focusing on passage retrieval for outside-knowledge visual question answering. |
Chen Qu; Hamed Zamani; Liu Yang; W. Bruce Croft; Erik Learned-Miller; | sigir | 2021-07-13 |
| 113 | Multi-Type Textual Reasoning for Product-Aware Answer Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a review-attribute heterogeneous graph neural network (abbreviated as RAHGNN) to model the logical relation of all multi-type text. |
Yue Feng; Zhaochun Ren; Weijie Zhao; Mingming Sun; Ping Li; | sigir | 2021-07-13 |
| 114 | Reinforcement Learning from Reformulations In Conversational Question Answering Over Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a step towards a more natural learning paradigm – from noisy and implicit feedback via question reformulations. |
Magdalena Kaiser; Rishiraj Saha Roy; Gerhard Weikum; | sigir | 2021-07-13 |
| 115 | How Much Can CLIP Benefit Vision-and-Language Tasks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To further study the advantage brought by CLIP, we propose to use CLIP as the visual encoder in various V&L models in two typical scenarios: 1) plugging CLIP into task-specific fine-tuning; 2) combining CLIP with V&L pre-training and transferring to downstream tasks. |
SHENG SHEN et. al. | arxiv-cs.CV | 2021-07-13 |
| 116 | Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple and effective strategy for data augmentation for low-resource machine reading comprehension (MRC). |
Hoang Van; Vikas Yadav; Mihai Surdeanu; | sigir | 2021-07-13 |
| 117 | Answer Complex Questions: Path Ranker Is All You Need Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a purely rank-based framework Thinking Path Re-Ranker (TPRR), which is comprised of Thinking Path Ranker (TPR) for generating document sequences called "a path" and External Path Reranker (EPR) for selecting the best path from candidate paths generated by TPR. |
XINYU ZHANG et. al. | sigir | 2021-07-13 |
| 118 | Deep Neural Networks Evolve Human-like Attention Distribution During Reading Comprehension Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we investigate whether humans and DNNs allocate attention in comparable ways when reading a text passage to subsequently answer a specific question. |
Jiajie Zou; Nai Ding; | arxiv-cs.CL | 2021-07-12 |
| 119 | Zero-shot Visual Question Answering Using Knowledge Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge these gaps, in this paper, we propose a Zero-shot VQA algorithm using knowledge graphs and a mask-based learning mechanism for better incorporating external knowledge, and present new answer-based Zero-shot VQA splits for the F-VQA dataset. |
ZHUO CHEN et. al. | arxiv-cs.AI | 2021-07-12 |
| 120 | PonderNet: Learning to Ponder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation we introduce PonderNet, a new algorithm that learns to adapt the amount of computation based on the complexity of the problem at hand. |
Andrea Banino; Jan Balaguer; Charles Blundell; | arxiv-cs.LG | 2021-07-12 |
| 121 | Similar Cases Recommendation Using Legal Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this demo, we describe our solution for predicting similar nodes in a case graph derived from our legal knowledge graph. |
Jaspreet Singh Dhani; Ruchika Bhatt; Balaji Ganesan; Parikshet Sirohi; Vasudha Bhatnagar; | arxiv-cs.AI | 2021-07-10 |
| 122 | DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on these observations, we propose a Dual-Visual Graph Reasoning Unit (DualVGR) which reasons over videos in an end-to-end fashion. |
Jianyu Wang; Bing-Kun Bao; Changsheng Xu; | arxiv-cs.MM | 2021-07-10 |
| 123 | An Initial Investigation of Non-Native Spoken Question-Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The SQA task considered in this paper is to extract the answer from a candidate$\text{‘}$s spoken response to a question in a prompt-response style language assessment test. |
Vatsal Raina; Mark J. F. Gales; | arxiv-cs.CL | 2021-07-09 |
| 124 | Benchmarking for Biomedical Natural Language Processing Tasks with A Domain Specific ALBERT Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present BioALBERT, a domain-specific adaptation of A Lite Bidirectional Encoder Representations from Transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine tuned for 6 different tasks across 20 benchmark datasets. |
Usman Naseem; Adam G. Dunn; Matloob Khushi; Jinman Kim; | arxiv-cs.CL | 2021-07-09 |
| 125 | Poolingformer: Long Document Modeling with Pooling Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a two-level attention schema, Poolingformer, for long document modeling. |
HANG ZHANG et. al. | icml | 2021-07-08 |
| 126 | LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we present LEGO, a Latent Execution-Guided reasOning framework to handle this challenge in KGQA. |
HONGYU REN et. al. | icml | 2021-07-08 |
| 127 | Learning to Rehearse in Long Sequence Memorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Rehearsal Memory (RM) to enhance long-sequence memorization by self-supervised rehearsal with a history sampler. |
ZHU ZHANG et. al. | icml | 2021-07-08 |
| 128 | Model Performance Scaling with Multiple Data Sources Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that there is a simple scaling law that predicts the loss incurred by a model even under varying dataset composition. |
Tatsunori Hashimoto; | icml | 2021-07-08 |
| 129 | Unifying Vision-and-Language Tasks Via Text Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate these hassles, in this work, we propose a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation, where our models learn to generate labels in text based on the visual and textual inputs. |
Jaemin Cho; Jie Lei; Hao Tan; Mohit Bansal; | icml | 2021-07-08 |
| 130 | A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a biologically inspired solution that solves this problem. |
Philipp Plank; Arjun Rao; Andreas Wild; Wolfgang Maass; | arxiv-cs.NE | 2021-07-08 |
| 131 | Reasoning Over Virtual Knowledge Bases With Open Predicate Relations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the Open Predicate Query Language (OPQL); a method for constructing a virtual KB (VKB) trained entirely from text. |
Haitian Sun; Patrick Verga; Bhuwan Dhingra; Ruslan Salakhutdinov; William W Cohen; | icml | 2021-07-08 |
| 132 | Bayesian Attention Belief Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights with a hierarchy of gamma distributions, and an encoder network by stacking Weibull distributions with a deterministic-upward-stochastic-downward structure to approximate the posterior. |
Shujian Zhang; Xinjie Fan; Bo Chen; Mingyuan Zhou; | icml | 2021-07-08 |
| 133 | MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Since most current medical VQA models focus on visual content, ignoring the importance of text, this paper proposes a multi-view attention-based model(MuVAM) for medical visual question answering which integrates the high-level semantics of medical images on the basis of text description. |
HAIWEI PAN et. al. | arxiv-cs.CV | 2021-07-07 |
| 134 | MedGPT: Medical Concept Prediction from Clinical Narratives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The data available in Electronic Health Records (EHRs) provides the opportunity to transform care, and the best way to provide better care for one patient is through learning from the data available on all other patients. |
ZELJKO KRALJEVIC et. al. | arxiv-cs.CL | 2021-07-07 |
| 135 | Probabilistic Graph Reasoning for Natural Proof Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the problem of reasoning over natural language statements. |
CHANGZHI SUN et. al. | arxiv-cs.CL | 2021-07-06 |
| 136 | SOCluster- Towards Intent-based Clustering of Stack Overflow Questions Using Graph-Based Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: It is here, we propose SOCluster, an approach and a tool to cluster SO questions based on intent using a graph-based clustering approach. |
Abhishek Kumar; Deep Ghadiyali; Sridhar Chimalakonda; | arxiv-cs.SE | 2021-07-06 |
| 137 | Neural Natural Language Processing for Unstructured Data in Electronic Health Records: A Review Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this survey paper, we summarize current neural NLP methods for EHR applications. |
IRENE LI et. al. | arxiv-cs.CL | 2021-07-06 |
| 138 | Question Answering Over Knowledge Graphs with Neural Machine Translation and Entity Linking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We rather propose a KGQA approach that delegates the processing of entities to entity linking (EL) systems. |
Daniel Diomedi; Aidan Hogan; | arxiv-cs.AI | 2021-07-06 |
| 139 | NOTE: Solution for KDD-CUP 2021 WikiKG90M-LSC Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we train the advanced algorithms in different domains to learn the triplets, including OTE, QuatE, RotatE and TransE. |
WEIYUE SU et. al. | arxiv-cs.IR | 2021-07-05 |
| 140 | No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a no-reference (NR) quality assessment metric for colored 3D models represented by both point cloud and mesh. |
ZICHENG ZHANG et. al. | arxiv-cs.CV | 2021-07-05 |
| 141 | A Knowledge-based Approach for Answering Complex Questions in Persian Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a knowledge-based approach for answering Persian complex questions using Farsbase; the Persian knowledge graph, exploiting PeCoQ; the newly created complex Persian question dataset. |
Romina Etezadi; Mehrnoush Shamsfard; | arxiv-cs.CL | 2021-07-05 |
| 142 | Mind Your Outliers! Investigating The Negative Impact of Outliers on Active Learning for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To understand this discrepancy, we profile 8 active learning methods on a per-example basis, and identify the problem as collective outliers — groups of examples that active learning methods prefer to acquire but models fail to learn (e.g., questions that ask about text in images or require external knowledge). |
Siddharth Karamcheti; Ranjay Krishna; Li Fei-Fei; Christopher D. Manning; | arxiv-cs.CL | 2021-07-05 |
| 143 | Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards the issue of introducing related knowledge, we propose a semantic-driven knowledge-aware QA framework, which controls the knowledge injection in a coarse-to-careful fashion. |
Luxi Xing; Yue Hu; Jing Yu; Yuqiang Xie; Wei Peng; | arxiv-cs.CL | 2021-07-04 |
| 144 | Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a dynamic working memory based cognitive VCR network, which stores accumulated commonsense between sentences to provide prior knowledge for inference. |
XUEJIAO TANG et. al. | arxiv-cs.CV | 2021-07-04 |
| 145 | Revisiting The Primacy of English in Zero-shot Cross-lingual Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our study, we compare English against other transfer languages for fine-tuning, on two pre-trained multilingual models (mBERT and mT5) and multiple classification and question answering tasks. |
Iulia Turc; Kenton Lee; Jacob Eisenstein; Ming-Wei Chang; Kristina Toutanova; | arxiv-cs.CL | 2021-06-30 |
| 146 | Zero-Shot Estimation of Base Models’ Weights in Ensemble of Machine Reading Comprehension Systems for Robust Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we leverage a zero-shot weighted ensemble method for improving the robustness of out-of-domain generalization in MRC models. |
Razieh Baradaran; Hossein Amirkhani; | arxiv-cs.CL | 2021-06-30 |
| 147 | Adventurer’s Treasure Hunt: A Transparent System for Visually Grounded Compositional Visual Question Answering Based on Scene Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With the expressed goal of improving system transparency and visual grounding in the reasoning process in VQA, we present a modular system for the task of compositional VQA based on scene graphs. |
Daniel Reich; Felix Putze; Tanja Schultz; | arxiv-cs.CV | 2021-06-28 |
| 148 | Overview of BioASQ 2020: The Eighth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an overview of the eighth edition of the BioASQ challenge, which ran as a lab in the Conference and Labs of the Evaluation Forum (CLEF) 2020. |
ANASTASIOS NENTIDIS et. al. | arxiv-cs.CL | 2021-06-28 |
| 149 | PeCoQ: A Dataset for Persian Complex Question Answering Over Knowledge Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss the dataset’s characteristics and describe our methodology for building it. |
Romina Etezadi; Mehrnoush Shamsfard; | arxiv-cs.CL | 2021-06-27 |
| 150 | Saying The Unseen: Video Descriptions Via Dialog Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a step towards the more practical application scenarios, we introduce a novel task that aims to describe a video using the natural language dialog between two agents as a supplementary information source given incomplete visual data. |
Ye Zhu; Yu Wu; Yi Yang; Yan Yan; | arxiv-cs.CV | 2021-06-26 |
| 151 | Weakly-Supervised Question Answering with Effective Rank and Weighted Loss Over Candidates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an effective method to learn a question answering model in a weak supervision way. |
Haozhe Qin; Jiangang Zhu; Beijun Shen; | www | 2021-06-25 |
| 152 | Cross-domain Knowledge Distillation for Retrieval-based Question Answering Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence in this work, we provide a new perspective on the potential of the teacher-student paradigm facilitating cross-domain transfer learning, where the teacher and student tasks belong to heterogeneous domains, with the goal to improve the student model’s performance in the target domain. |
CEN CHEN et. al. | www | 2021-06-25 |
| 153 | A Linguistic Study on Relevance Modeling in Information Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We proposed three intervention methods to investigate how to leverage different modeling focuses of relevance to improve these IR tasks. |
YIXING FAN et. al. | www | 2021-06-25 |
| 154 | Multimodal Few-Shot Learning with Frozen Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present a simple, yet effective, approach for transferring this few-shot learning ability to a multimodal setting (vision and language). |
MARIA TSIMPOUKELLI et. al. | arxiv-cs.CV | 2021-06-25 |
| 155 | Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we suggest that KBQA models should have three levels of built-in generalization: i.i.d., compositional, and zero-shot. |
YU GU et. al. | www | 2021-06-25 |
| 156 | Joint Spatio-Textual Reasoning for Answering Tourism Questions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to answer real-world tourism questions that seek Points-of-Interest (POI) recommendations. |
Danish Contractor; Shashank Goel; Mausam; Parag Singla; | www | 2021-06-25 |
| 157 | ComQA: Compositional Question Answering Via Hierarchical Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a large-scale compositional question answering dataset containing more than 120k human-labeled questions. |
Bingning Wang; Ting Yao; Weipeng Chen; Jingfang Xu; Xiaochuan Wang; | www | 2021-06-25 |
| 158 | Cross-lingual Language Model Pretraining for Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce two novel retrieval-oriented pretraining tasks to further pretrain cross-lingual language models for downstream retrieval tasks such as cross-lingual ad-hoc retrieval (CLIR) and cross-lingual question answering (CLQA). |
Puxuan Yu; Hongliang Fei; Ping Li; | www | 2021-06-25 |
| 159 | Wiki2Prop: A Multimodal Approach for Predicting Wikidata Properties from Wikipedia Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on entities with a dedicated Wikipedia page in any language to make predictions directly based on textual content. |
Michael Luggen; Julien Audiffren; Djellel Difallah; Philippe Cudré-Mauroux; | www | 2021-06-25 |
| 160 | A Picture May Be Worth A Hundred Words for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to take description-question pairs as input, instead of deep visual features, and fed them into a language-only Transformer model, simplifying the process and the computational cost. |
YUSUKE HIROTA et. al. | arxiv-cs.CV | 2021-06-25 |
| 161 | Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects. |
Long Hoang Dang; Thao Minh Le; Vuong Le; Truyen Tran; | arxiv-cs.CV | 2021-06-25 |
| 162 | Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this, we propose a fully Transformer visual embedding for VLP to better learn visual relation and further promote inter-modal alignment. |
HONGWEI XUE et. al. | arxiv-cs.CV | 2021-06-25 |
| 163 | Search Engines Vs. Symptom Checkers: A Comparison of Their Effectiveness for Online Health Advice Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we conducted a user study with 64 real-world users performing 8 simulated self-diagnosis tasks. |
Sebastian Cross; Ahmed Mourad; Guido Zuccon; Bevan Koopman; | www | 2021-06-25 |
| 164 | Multilingual COVID-QA: Learning Towards Global Information Sharing Via Web Question Answering in Multiple Languages Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a multilingual COVID-QA model to answer people’s questions in their own languages while the model is able to absorb knowledge from other languages. |
RUI YAN et. al. | www | 2021-06-25 |
| 165 | A Workflow Analysis of Context-driven Conversational Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to understand a general workflow of natural context-driven conversational recommendation that arises from a pairwise study of a human user interacting with a human simulating the role of a recommender. |
Shengnan Lyu; Arpit Rana; Scott Sanner; Mohamed Reda Bouadjenek; | www | 2021-06-25 |
| 166 | Extracting Contextualized Quantity Facts from Web Tables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To enable such queries over web contents, this paper develops a novel method for automatically extracting quantity facts from ad-hoc web tables. |
Vinh Thinh Ho; Koninika Pal; Simon Razniewski; Klaus Berberich; Gerhard Weikum; | www | 2021-06-25 |
| 167 | Information Extraction From Co-Occurring Similar Entities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how information extracted from similar entities that co-occur in structures like tables or lists can help to increase the coverage of such knowledge graphs. |
Nicolas Heist; Heiko Paulheim; | www | 2021-06-25 |
| 168 | Generating Accurate Caption Units for Figure Captioning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We formulate the caption unit generation problem as a controlled captioning problem. Given a caption unit type as a control signal, a model generates an accurate caption unit of that type. |
XIN QIAN et. al. | www | 2021-06-25 |
| 169 | Taxonomy-aware Learning for Few-Shot Event Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To deal with the low-resources problem, we investigate few-shot event detection in this paper and propose TaLeM, a novel taxonomy-aware learning model, consisting of two components, i.e., the taxonomy-aware self-supervised learning framework (TaSeLF) and the taxonomy-aware prototypical networks (TaPN). |
Jianming Zheng; Fei Cai; Wanyu Chen; Wengqiang Lei; Honghui Chen; | www | 2021-06-25 |
| 170 | Semi-Open Information Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we define a new task, namely Semi-Open Information Extraction (SOIE), to address this need. |
BOWEN YU et. al. | www | 2021-06-25 |
| 171 | Advanced Semantics for Commonsense Knowledge Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a methodology, called Ascent, to automatically build a large-scale knowledge base (KB) of CSK assertions, with advanced expressiveness and both better precision and recall than prior works. |
Tuan-Phong Nguyen; Simon Razniewski; Gerhard Weikum; | www | 2021-06-25 |
| 172 | AIT-QA: Question Answering Dataset Over Complex Tables in The Airline Industry Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we introduce the domain-specific Table QA dataset AIT-QA (Airline Industry Table QA). |
YANNIS KATSIS et. al. | arxiv-cs.CL | 2021-06-24 |
| 173 | VOGUE: Answer Verbalization Through Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this context, we propose a multi-task-based answer verbalization framework: VOGUE (Verbalization thrOuGh mUlti-task lEarning). |
Endri Kacupaj; Shyamnath Premnadh; Kuldeep Singh; Jens Lehmann; Maria Maleshkova; | arxiv-cs.CL | 2021-06-24 |
| 174 | OKGIT: Open Knowledge Graph Link Prediction with Implicit Types Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this problem in this work and propose OKGIT that improves OpenKG link prediction using novel type compatibility score and type regularization. |
Chandrahas; Partha Pratim Talukdar; | arxiv-cs.CL | 2021-06-24 |
| 175 | ParaLaw Nets — Cross-lingual Sentence-level Pretraining for Legal Text Processing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: From that observation, in this paper, we propose ParaLaw Nets, a pretrained model family using sentence-level cross-lingual information to reduce ambiguity and increase the performance in legal text processing. |
HA-THANH NGUYEN et. al. | arxiv-cs.CL | 2021-06-24 |
| 176 | PALRACE: Reading Comprehension Dataset with Human Data and Labeled Rationales Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To facilitate supervised learning of human rationales, here we present PALRACE (Pruned And Labeled RACE), a new MRC dataset with human labeled rationales for 800 passages selected from the RACE dataset. |
JIAJIE ZOU et. al. | arxiv-cs.CL | 2021-06-23 |
| 177 | ABCD: A Graph Framework to Convert Complex Sentences to A Covering Set of Simple Sentences Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new task to decompose each complex sentence into simple sentences derived from the tensed clauses in the source, and a novel problem formulation as a graph edit task. |
Yanjun Gao; Ting-hao; Huang; Rebecca J. Passonneau; | arxiv-cs.CL | 2021-06-22 |
| 178 | Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel and easy-to-apply data augmentation strategy, namely Bilateral Generation (BiG), with a contrastive training objective for improving the performance of ranking question answer pairs with existing labeled data. |
Yang Deng; Wenxuan Zhang; Wai Lam; | arxiv-cs.CL | 2021-06-21 |
| 179 | Fine-tune The Entire RAG Architecture (including DPR Retriever) for Question-Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner. |
Shamane Siriwardhana; Rivindu Weerasekera; Elliott Wen; Suranga Nanayakkara; | arxiv-cs.IR | 2021-06-21 |
| 180 | VQA-Aid: Visual Question Answering for Post-Disaster Damage Assessment and Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address the importance of \textit{visual question answering (VQA)} task for post-disaster damage assessment by presenting our recently developed VQA dataset called \textit{HurMic-VQA} collected during hurricane Michael, and comparing the performances of baseline VQA models. |
Argho Sarkar; Maryam Rahnemoonfar; | arxiv-cs.CV | 2021-06-19 |
| 181 | SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering Over Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose SPBERT, a transformer-based language model pre-trained on massive SPARQL query logs. |
Hieu Tran; Long Phan; James Anibal; Binh T. Nguyen; Truong-Son Nguyen; | arxiv-cs.CL | 2021-06-18 |
| 182 | Weakly Supervised Pre-Training for Multi-Hop Retriever Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the issue, we propose a new method for weakly supervised multi-hop retriever pre-training without human efforts. |
Yeon Seonwoo; Sang-Woo Lee; Ji-Hoon Kim; Jung-Woo Ha; Alice Oh; | arxiv-cs.CL | 2021-06-18 |
| 183 | Modeling Worlds in Text Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a dataset that enables the creation of learning agents that can build knowledge graph-based world models of interactive narratives. |
Prithviraj Ammanabrolu; Mark O. Riedl; | arxiv-cs.CL | 2021-06-17 |
| 184 | DocNLI: A Large-scale Dataset for Document-level Natural Language Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents DocNLI — a newly-constructed large-scale dataset for document-level NLI. |
Wenpeng Yin; Dragomir Radev; Caiming Xiong; | arxiv-cs.CL | 2021-06-17 |
| 185 | Disentangling Online Chats with DAG-Structured LSTMs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we apply DAG-LSTMs to the conversation disentanglement task. |
Duccio Pappadopulo; Lisa Bauer; Marco Farina; Ozan İrsoy; Mohit Bansal; | arxiv-cs.CL | 2021-06-16 |
| 186 | An Intelligent Question Answering System Based on Power Knowledge Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article introduced a domain knowledge graph using the graph database and graph computing technologies from massive heterogeneous data in electric power. |
YACHEN TANG et. al. | arxiv-cs.AI | 2021-06-16 |
| 187 | Probing Image-Language Transformers for Verb Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To do so, we collect a dataset of image-sentence pairs (in English) consisting of 421 verbs that are either visual or commonly found in the pretraining data (i.e., the Conceptual Captions dataset). |
Lisa Anne Hendricks; Aida Nematzadeh; | arxiv-cs.CL | 2021-06-16 |
| 188 | How Modular Should Neural Module Networks Be for Systematic Generalization? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate that the stage and the degree at which modularity is defined has large influence on systematic generalization. |
Vanessa D’Amario; Tomotake Sasaki; Xavier Boix; | arxiv-cs.LG | 2021-06-15 |
| 189 | Question Answering Infused Pre-training of General-Purpose Contextualized Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a pre-training objective based on question answering (QA) for learning general-purpose contextual representations, motivated by the intuition that the representation of a phrase in a passage should encode all questions that the phrase can answer in context. |
Robin Jia; Mike Lewis; Luke Zettlemoyer; | arxiv-cs.CL | 2021-06-15 |
| 190 | Analysing Dense Passage Retrieval for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide an in-depth evaluation of such models not only unveiling the reasons behind their success but also their limitations. |
Georgios Sidiropoulos; Nikos Voskarides; Svitlana Vakulenko; Evangelos Kanoulas; | arxiv-cs.IR | 2021-06-15 |
| 191 | Exploiting Sentence-Level Representations for Passage Ranking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explicitly model the sentence-level representations by using Dynamic Memory Networks (DMNs) and conduct empirical evaluation to show improvements in passage re-ranking over fine-tuned vanilla BERT models by memory-enhanced explicit sentence modelling on a diverse set of open-domain QA datasets. |
Jurek Leonhardt; Fabian Beringer; Avishek Anand; | arxiv-cs.IR | 2021-06-14 |
| 192 | Memory-efficient Transformers Via Top-$k$ Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a simple yet highly accurate approximation for vanilla attention. |
Ankit Gupta; Guy Dar; Shaya Goodman; David Ciprut; Jonathan Berant; | arxiv-cs.CL | 2021-06-12 |
| 193 | NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. |
Junbin Xiao; Xindi Shang; Angela Yao; Tat-Seng Chua; | cvpr | 2021-06-11 |
| 194 | Less Is More: ClipBERT for Video-and-Language Learning Via Sparse Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To provide a remedy to this dilemma, we propose a generic framework CLIPBERT that enables affordable end-to-end learning for video-and-language tasks, by employing sparse sampling, where only a single or a few sparsely sampled short clips from a video are used at each training step. |
JIE LEI et. al. | cvpr | 2021-06-11 |
| 195 | Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We take a step further in pushing the limits of vision-and-language pre-training data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [Sharma et al. 2018] and introduce the Conceptual 12M (CC12M), a dataset with 12 million image-text pairs specifically meant to be used for vision-and-language pre-training. |
Soravit Changpinyo; Piyush Sharma; Nan Ding; Radu Soricut; | cvpr | 2021-06-11 |
| 196 | Vx2Text: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Vx2Text, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. |
XUDONG LIN et. al. | cvpr | 2021-06-11 |
| 197 | Roses Are Red, Violets Are Blue… But Should VQA Expect Them To? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we claim that the standard evaluation metric, which consists in measuring the overall in-domain accuracy, is misleading. |
Corentin Kervadec; Grigory Antipov; Moez Baccouche; Christian Wolf; | cvpr | 2021-06-11 |
| 198 | Bridge To Answer: Structure-Aware Graph Interaction Network for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel method, termed Bridge to Answer, to infer correct answers for questions about a given video by leveraging adequate graph interactions of heterogeneous crossmodal graphs. |
Jungin Park; Jiyoung Lee; Kwanghoon Sohn; | cvpr | 2021-06-11 |
| 199 | PQA: Perceptual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we rejuvenate the study of perceptual organization, by advocating two positional changes: (i) we examine purposefully generated synthetic data, instead of complex real imagery, and (ii) we ask machines to synthesize novel perceptually-valid patterns, instead of explaining existing data. |
Yonggang Qi; Kai Zhang; Aneeshan Sain; Yi-Zhe Song; | cvpr | 2021-06-11 |
| 200 | Found A Reason for Me? Weakly-supervised Grounded Visual Question Answering Using Capsules Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on a more relaxed setting: the grounding of relevant visual entities in a weakly supervised manner by training on the VQA task alone. |
AISHA UROOJ et. al. | cvpr | 2021-06-11 |
| 201 | Look Before You Speak: Visually Contextualized Utterances Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a solution in the form of a new visually conditioned Future Utterance Prediction task. |
Paul Hongsuck Seo; Arsha Nagrani; Cordelia Schmid; | cvpr | 2021-06-11 |
| 202 | Predicting Human Scanpaths in Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new deep reinforcement learning method to predict scanpaths leading to different performances in visual question answering. |
Xianyu Chen; Ming Jiang; Qi Zhao; | cvpr | 2021-06-11 |
| 203 | UC2: Universal Cross-Lingual Cross-Modal Vision-and-Language Pre-Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To generalize this success to non-English languages, we introduce UC^2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. |
MINGYANG ZHOU et. al. | cvpr | 2021-06-11 |
| 204 | TAP: Text-Aware Pre-Training for Text-VQA and Text-Caption Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. |
ZHENGYUAN YANG et. al. | cvpr | 2021-06-11 |
| 205 | Perception Matters: Detecting Perception Failures of VQA Models Using Metamorphic Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the principles of software metamorphic testing, we introduce MetaVQA, a model-agnostic framework for benchmarking perception capability of VQA models. |
Yuanyuan Yuan; Shuai Wang; Mingyue Jiang; Tsong Yueh Chen; | cvpr | 2021-06-11 |
| 206 | AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Action Genome Question Answering (AGQA), a new benchmark for compositional spatio-temporal reasoning. |
Madeleine Grunde-McLaughlin; Ranjay Krishna; Maneesh Agrawala; | cvpr | 2021-06-11 |
| 207 | RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To prove the generality of our proposals, we apply the two modules to the vanilla transformer model to build our Relationship-Sensitive Transformer (RSTNet) for image captioning task. |
XUYING ZHANG et. al. | cvpr | 2021-06-11 |
| 208 | How Transferable Are Reasoning Patterns in VQA? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that uncertainty in vision is a dominating factor preventing the successful learning of reasoning in vision and language problems. |
CORENTIN KERVADEC et. al. | cvpr | 2021-06-11 |
| 209 | Domain-Robust VQA With Diverse Datasets and Methods But No Target Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Second, we test the robustness of different families of VQA methods (classic two-stream, transformer, and neuro-symbolic methods) to these shifts. Third, we test the applicability of existing domain adaptation methods and devise a new one to bridge VQA domain gaps, adjusted to specific VQA models. |
Mingda Zhang; Tristan Maidment; Ahmad Diab; Adriana Kovashka; Rebecca Hwa; | cvpr | 2021-06-11 |
| 210 | TellMeWhy: A Dataset for Answering Why-Questions in Narratives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce TellMeWhy, a new crowd-sourced dataset that consists of more than 30k questions and free-form answers concerning why characters in short narratives perform the actions described. |
Yash Kumar Lal; Nathanael Chambers; Raymond Mooney; Niranjan Balasubramanian; | arxiv-cs.CL | 2021-06-10 |
| 211 | NAAQA: A Neural Architecture for Acoustic Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, based on the previously introduced CLEAR dataset, we propose a new benchmark for AQA that emphasizes the specific challenges of acoustic inputs, e.g. variable duration scenes. |
Jerome Abdelnour; Jean Rouat; Giampiero Salvi; | arxiv-cs.CL | 2021-06-10 |
| 212 | What Would A Teacher Do? Predicting Future Talk Moves Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new task, called future talk move prediction (FTMP): it consists of predicting the next talk move — an utterance strategy from APT — given a conversation history with its corresponding talk moves. |
Ananya Ganesh; Martha Palmer; Katharina Kann; | arxiv-cs.CL | 2021-06-09 |
| 213 | DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce DESCGEN: given mentions spread over multiple documents, the goal is to generate an entity summary description. |
Weijia Shi; Mandar Joshi; Luke Zettlemoyer; | arxiv-cs.CL | 2021-06-09 |
| 214 | End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. |
Devendra Singh Sachan; Siva Reddy; William Hamilton; Chris Dyer; Dani Yogatama; | arxiv-cs.CL | 2021-06-09 |
| 215 | CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the first end-to-end, transformer-based table question answering (QA) system that takes natural language questions and massive table corpus as inputs to retrieve the most relevant tables and locate the correct table cells to answer the question. In addition, we introduce two new open-domain benchmarks, E2E_WTQ and E2E_GNQ, consisting of 2,005 natural language questions over 76,242 tables. |
Feifei Pan; Mustafa Canim; Michael Glass; Alfio Gliozzo; Peter Fox; | arxiv-cs.CL | 2021-06-08 |
| 216 | Check It Again: Progressive Visual Question Answering Via Visual Entailment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a select-and-rerank (SAR) progressive framework based on Visual Entailment. |
Qingyi Si; Zheng Lin; Mingyu Zheng; Peng Fu; Weiping Wang; | arxiv-cs.CV | 2021-06-08 |
| 217 | PAM: Understanding Product Images in Cross Product Category Attribute Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a more inclusive framework that fully utilizes these different modalities for attribute extraction. |
RONGMEI LIN et. al. | arxiv-cs.CV | 2021-06-08 |
| 218 | VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To facilitate the evaluation of such systems, we introduce Video-And-Language Understanding Evaluation (VALUE) benchmark, an assemblage of 11 VidL datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. |
LINJIE LI et. al. | arxiv-cs.CV | 2021-06-08 |
| 219 | XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop a new task-agnostic distillation framework XtremeDistilTransformers that leverages the advantage of task-specific methods for learning a small universal model that can be applied to arbitrary tasks and languages. |
Subhabrata Mukherjee; Ahmed Hassan Awadallah; Jianfeng Gao; | arxiv-cs.CL | 2021-06-08 |
| 220 | Comprehension Based Question Answering Using Bloom’s Taxonomy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Bloom’s Taxonomy helps educators teach children how to use knowledge by categorizing comprehension skills, so we use it to analyze and improve the comprehension skills of large pre-trained language models. |
Pritish Sahu; Michael Cogswell; Sara Rutherford-Quach; Ajay Divakaran; | arxiv-cs.CL | 2021-06-08 |
| 221 | Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new challenge question answering dataset, Disfl-QA, a derivative of SQuAD, where humans introduce contextual disfluencies in previously fluent questions. |
Aditya Gupta; Jiacheng Xu; Shyam Upadhyay; Diyi Yang; Manaal Faruqui; | arxiv-cs.CL | 2021-06-07 |
| 222 | Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work provides a comprehensive and quantitative analysis about the difficulty of Book QA: (1) We benchmark the research on the NarrativeQA dataset with extensive experiments with cutting-edge ODQA techniques. |
XIANGYANG MOU et. al. | arxiv-cs.CL | 2021-06-07 |
| 223 | Enhancing Taxonomy Completion with Concept Generation Via Fusing Relational Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve the limitations of extraction-based methods, we propose GenTaxo to enhance taxonomy completion by identifying positions in existing taxonomies that need new concepts and then generating appropriate concept names. |
Qingkai Zeng; Jinfeng Lin; Wenhao Yu; Jane Cleland-Huang; Meng Jiang; | arxiv-cs.CL | 2021-06-05 |
| 224 | BERTnesia: Investigating The Capture and Forgetting of Knowledge in BERT Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article, we probe BERT specifically to understand and measure the relational knowledge it captures in its parametric memory. |
Jonas Wallat; Jaspreet Singh; Avishek Anand; | arxiv-cs.CL | 2021-06-05 |
| 225 | Human-Adversarial Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to stress test VQA models, we benchmark them against human-adversarial examples. |
SASHA SHENG et. al. | arxiv-cs.CV | 2021-06-04 |
| 226 | Prediction or Comparison: Toward Interpretable Qualitative Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we categorize qualitative reasoning tasks into two types: prediction and comparison. |
Mucheng Ren; Heyan Huang; Yang Gao; | arxiv-cs.CL | 2021-06-04 |
| 227 | MERLOT: Multimodal Neural Script Knowledge Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech — in an entirely label-free, self-supervised manner. |
ROWAN ZELLERS et. al. | arxiv-cs.CV | 2021-06-04 |
| 228 | Syntax-augmented Multilingual BERT for Cross-lingual Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work shows that explicitly providing language syntax and training mBERT using an auxiliary objective to encode the universal dependency tree structure helps cross-lingual transfer. |
Wasi Uddin Ahmad; Haoran Li; Kai-Wei Chang; Yashar Mehdad; | arxiv-cs.CL | 2021-06-03 |
| 229 | Self-supervised Dialogue Learning for Spoken Conversational Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we introduce a self-supervised learning approach, including incoherence discrimination, insertion detection, and question prediction, to explicitly capture the coreference resolution and dialogue coherence among spoken documents. |
Nuo Chen; Chenyu You; Yuexian Zou; | arxiv-cs.CL | 2021-06-03 |
| 230 | Grounding Complex Navigational Instructions Using Scene Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We adapt the CLEVR visual question answering dataset to generate complex natural language navigation instructions and accompanying scene graphs, yielding an environment-agnostic supervised dataset. |
Michiel de Jong; Satyapriya Krishna; Anuva Agarwal; | arxiv-cs.LG | 2021-06-03 |
| 231 | Minimax and Neyman-Pearson Meta-Learning for Outlier Languages Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In light of this, we propose a new adaptive optimiser solving for a local approximation to their Nash equilibrium. |
Edoardo Maria Ponti; Rahul Aralikatte; Disha Shrivastava; Siva Reddy; Anders Søgaard; | arxiv-cs.CL | 2021-06-02 |
| 232 | Answer Generation for Retrieval-based Question Answering Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to generate answers from a set of AS2 top candidates. |
Chao-Chun Hsu; Eric Lind; Luca Soldaini; Alessandro Moschitti; | arxiv-cs.CL | 2021-06-02 |
| 233 | Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we propose a new language understanding task, Linguistic Ethical Interventions (LEI), where the goal is to amend a question-answering (QA) model’s unethical behavior by communicating context-specific principles of ethics and equity to it. |
Jieyu Zhao; Daniel Khashabi; Tushar Khot; Ashish Sabharwal; Kai-Wei Chang; | arxiv-cs.CL | 2021-06-02 |
| 234 | Knowing More About Questions Can Help: Improving Calibration in Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study calibration in question answering, estimating whether model correctly predicts answer for each question. |
Shujian Zhang; Chengyue Gong; Eunsol Choi; | arxiv-cs.CL | 2021-06-02 |
| 235 | On The Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We use this pruning technique in conjunction with quantizing the attention values to only a 3-bit format, without retraining, resulting in only a 0.8% accuracy reduction on question answering with fine-tuned RoBERTa. |
TIANCHU JI et. al. | arxiv-cs.CL | 2021-06-02 |
| 236 | Ember: No-Code Context Enrichment Via Similarity-Based Keyless Joins Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we propose Ember, a system that abstracts and automates keyless joins to generalize context enrichment. |
Sahaana Suri; Ihab F. Ilyas; Christopher Ré; Theodoros Rekatsinas; | arxiv-cs.DB | 2021-06-02 |
| 237 | Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel NLP task of identifying directed sentiment relationship between political entities from a given news document, which we call directed sentiment extraction. From a million-scale news corpus, we construct a dataset of news sentences where sentiment relations of political entities are manually annotated. |
Kunwoo Park; Zhufeng Pan; Jungseock Joo; | arxiv-cs.CL | 2021-06-02 |
| 238 | Multilingual Medical Question Answering and Information Retrieval for Rural Health Intelligence Access Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe an approach leveraging the phenomenal progress in Machine Learning and NLP (Natural Language Processing) techniques to design a model that is low-resource, multilingual, and a preliminary first-point-of-contact medical assistant. |
Vishal Vinod; Susmit Agrawal; Vipul Gaurav; Pallavi R; Savita Choudhary; | arxiv-cs.CL | 2021-06-02 |
| 239 | Adversarial VQA: A New Benchmark for Evaluating The Robustness of VQA Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To study this, we introduce Adversarial VQA, a new large-scale VQA benchmark, collected iteratively via an adversarial human-and-model-in-the-loop procedure. |
Linjie Li; Jie Lei; Zhe Gan; Jingjing Liu; | arxiv-cs.CV | 2021-06-01 |
| 240 | Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the opportunities and challenges, in this paper we describe our novel practice in Microsoft to leverage such large amounts of unlabeled data in target languages in real production settings. |
SHINING LIANG et. al. | arxiv-cs.CL | 2021-06-01 |
| 241 | A Coarse to Fine Question Answering System Based on Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a coarse to fine question answering (CFQA) system based on reinforcement learning which can efficiently processes documents with different lengths by choosing appropriate actions. |
Yu Wang; Hongxia Jin; | arxiv-cs.CL | 2021-06-01 |
| 242 | DoT: An Efficient Double Transformer for NLP Tasks with Tables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To improve efficiency while maintaining a high accuracy, we propose a new architecture, DoT, a double transformer model, that decomposes the problem into two sub-tasks: A shallow pruning transformer that selects the top-K tokens, followed by a deep task-specific transformer that takes as input those K tokens. |
Syrine Krichene; Thomas Müller; Julian Martin Eisenschlos; | arxiv-cs.CL | 2021-06-01 |
| 243 | Conversational Question Answering: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This survey, therefore, is an effort to present a comprehensive review of the state-of-the-art research trends of CQA primarily based on reviewed papers from 2016-2021. |
Munazza Zaib; Wei Emma Zhang; Quan Z. Sheng; Adnan Mahmood; Yang Zhang; | arxiv-cs.CL | 2021-06-01 |
| 244 | ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this gap, we design annotation protocols motivated by an issues–viewpoints–assertions framework to crowdsource four new datasets on diverse online conversation forms of news comments, discussion forums, community question answering forums, and email threads. |
ALEXANDER R. FABBRI et. al. | arxiv-cs.CL | 2021-06-01 |
| 245 | Question-aware Transformer Models for Consumer Health Question Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the task of abstractive summarization for real-world consumer health questions. |
Shweta Yadav; Deepak Gupta; Asma Ben Abacha; Dina Demner-Fushman; | arxiv-cs.CL | 2021-06-01 |
| 246 | Parameter-Efficient Neural Question Answering Models Via Graph-Enriched Document Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that a GCN enriched document representation greatly improves the results seen in HotPotQA, even when using a trivial topology. |
Louis Castricato; Stephen Fitz; Won Young Shin; | arxiv-cs.CL | 2021-06-01 |
| 247 | Bangla Natural Language Processing: A Comprehensive Review of Classical, Machine Learning, and Deep Learning Based Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we present a thorough review of 71 BNLP research papers and categorize them into 11 categories, namely Information Extraction, Machine Translation, Named Entity Recognition, Parsing, Parts of Speech Tagging, Question Answering System, Sentiment Analysis, Spam and Fake Detection, Text Summarization, Word Sense Disambiguation, and Speech Processing and Recognition. |
OVISHAKE SEN et. al. | arxiv-cs.CL | 2021-05-31 |
| 248 | Corpus-Based Paraphrase Detection Experiments and Review Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we give a performance overview of various types of corpus-based models, especially deep learning (DL) models, with the task of paraphrase detection. |
Tedo Vrbanec; Ana Mestrovic; | arxiv-cs.CL | 2021-05-31 |
| 249 | End-to-End Multihop Retrieval for Compositional Question Answering Over Long Documents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a multi-hop retrieval method, DocHopper, to answer compositional questions over long documents. |
Haitian Sun; William W. Cohen; Ruslan Salakhutdinov; | arxiv-cs.CL | 2021-05-31 |
| 250 | A Compression-Compilation Framework for On-mobile Real-time BERT Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a compression-compilation co-design framework that can guarantee the identified model to meet both resource and real-time specifications of mobile devices. |
WEI NIU et. al. | arxiv-cs.LG | 2021-05-30 |
| 251 | GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on solving geometric problems, which requires a comprehensive understanding of textual descriptions, visual diagrams, and theorem knowledge. |
JIAQI CHEN et. al. | arxiv-cs.AI | 2021-05-30 |
| 252 | Is Sluice Resolution Really Just Question Answering? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Sluice resolution is a problem where a system needs to output the corresponding antecedents of wh-ellipses. The antecedents are elided contents behind the wh-words but are … |
Peratham Wiriyathammabhum; | arxiv-cs.CL | 2021-05-29 |
| 253 | Inside ASCENT: Exploring A Deep Commonsense Knowledge Base and Its Usage in Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this demo, we present a web portal that allows users to understand its construction process, explore its content, and observe its impact in the use case of question answering. |
Tuan-Phong Nguyen; Simon Razniewski; Gerhard Weikum; | arxiv-cs.AI | 2021-05-28 |
| 254 | Feature Extraction and Evaluation for BioMedical Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present our work on the BioASQ pipeline. |
Ankit Shah; Srishti Singh; Shih-Yen Tao; | arxiv-cs.CL | 2021-05-28 |
| 255 | Improve Query Focused Abstractive Summarization By Incorporating Answer Relevance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose QFS-BART, a model that incorporates the explicit answer relevance of the source documents given the query via a question answering model, to generate coherent and answer-related summaries. |
Dan Su; Tiezheng Yu; Pascale Fung; | arxiv-cs.CL | 2021-05-27 |
| 256 | Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering The 2002 Gujarat Violence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We combine corpus-level evaluation requirements with a real-world, social science setting and introduce the IndiaPoliceEvents corpus–all 21,391 sentences from 1,257 English-language Times of India articles about events in the state of Gujarat during March 2002. |
Andrew Halterman; Katherine A. Keith; Sheikh Muhammad Sarwar; Brendan O’Connor; | arxiv-cs.CL | 2021-05-27 |
| 257 | Multi-turn Dialog System on Single-turn Data in Medical Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This research is focused on the multi-turn dialog system trained on the multi-turn dialog data. |
NAZIB SORATHIYA et. al. | arxiv-cs.CL | 2021-05-26 |
| 258 | Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new framework to exploit more valid facts while obtaining explainability for multi-hop QA by dynamically constructing a semantic graph and reasoning over it. |
Weiwen Xu; Huihui Zhang; Deng Cai; Wai Lam; | arxiv-cs.CL | 2021-05-25 |
| 259 | Few-Shot Upsampling for Protest Size Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new task and dataset for a common problem in social science research: upsampling coarse document labels to fine-grained labels or spans. We pose the problem in a question answering format, with the answers providing the fine-grained labels. We provide a benchmark dataset and baselines on a socially impactful task: identifying the exact crowd size at protests and demonstrations in the United States given only order-of-magnitude information about protest attendance, a very small sample of fine-grained examples, and English-language news text. |
Andrew Halterman; Benjamin J. Radford; | arxiv-cs.CL | 2021-05-24 |
| 260 | A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we elaborately summarize the typical challenges and solutions for complex KBQA. |
YUNSHI LAN et. al. | arxiv-cs.CL | 2021-05-24 |
| 261 | VANiLLa : Verbalized Answers in Natural Language at Large Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence, we provide the VANiLLa dataset which aims at reducing this gap by offering answers in natural language sentences. |
Debanjali Biswas; Mohnish Dubey; Md Rashad Al Hasan Rony; Jens Lehmann; | arxiv-cs.CL | 2021-05-24 |
| 262 | Multi-modal Understanding and Generation for Medical Images and Text Via Vision-Language Pre-Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we explore a broad set of multi-modal representation learning tasks in the medical domain, specifically using radiology images and the unstructured report. |
Jong Hak Moon; Hyungyung Lee; Woncheol Shin; Edward Choi; | arxiv-cs.CV | 2021-05-24 |
| 263 | Open Domain Question Answering Over Tables Via Dense Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a retriever designed to handle tabular context. |
Jonathan Herzig; Thomas M�ller; Syrine Krichene; Julian Eisenschlos; | naacl | 2021-05-23 |
| 264 | Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, however, we verbalize the entire English Wikidata KG, and discuss the unique challenges associated with a broad, open-domain, large-scale verbalization. |
Oshin Agarwal; Heming Ge; Siamak Shakeri; Rami Al-Rfou; | naacl | 2021-05-23 |
| 265 | RECONSIDER: Improved Re-Ranking Using Span-Focused Cross-Attention for Open Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a successful re-ranking approach (RECONSIDER) for span-extraction tasks that improves upon the performance of MRC models, even beyond large-scale pre-training. |
Srinivasan Iyer; Sewon Min; Yashar Mehdad; Wen-tau Yih; | naacl | 2021-05-23 |
| 266 | Capturing Row and Column Semantics in Transformer Based Question Answering Over Tables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose two novel approaches demonstrating that one can achieve superior performance on table QA task without even using any of these specialized pre-training techniques. |
MICHAEL GLASS et. al. | naacl | 2021-05-23 |
| 267 | Robust Question Answering Through Sub-part Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To make a more robust and understandable QA system, we model question answering as an alignment problem. |
Jifan Chen; Greg Durrett; | naacl | 2021-05-23 |
| 268 | MIMOQA: Multimodal Input Multimodal Output Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel task – MIMOQA – Multimodal Input Multimodal Output Question Answering in which the output is also multimodal. |
HRITURAJ SINGH et. al. | naacl | 2021-05-23 |
| 269 | Adaptable and Interpretable Neural MemoryOver Symbolic Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we develop a neural LM that includes an interpretable neuro-symbolic KB in the form of a fact memory. |
Pat Verga; Haitian Sun; Livio Baldini Soares; William Cohen; | naacl | 2021-05-23 |
| 270 | Open-Domain Question Answering Goes Conversational Via Question Rewriting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. |
RAVITEJA ANANTHA et. al. | naacl | 2021-05-23 |
| 271 | Hierarchical Transformer for Task Oriented Dialog Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generalized framework for Hierarchical Transformer Encoders and show how a standard transformer can be morphed into any hierarchical encoder, including HRED and HIBERT like models, by using specially designed attention masks and positional encodings. |
Bishal Santra; Potnuru Anusha; Pawan Goyal; | naacl | 2021-05-23 |
| 272 | On The Transferability of Minimal Prediction Preserving Inputs in Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the context of question answering, we investigate competing hypotheses for the existence of MPPIs, including poor posterior calibration of neural models, lack of pretraining, and dataset bias (where a model learns to attend to spurious, non-generalizable cues in the training data). |
Shayne Longpre; Yi Lu; Chris DuBois; | naacl | 2021-05-23 |
| 273 | Hurdles to Progress in Long-form Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While many models have recently been proposed for LFQA, we show in this paper that the task formulation raises fundamental challenges regarding evaluation and dataset creation that currently preclude meaningful modeling progress. |
Kalpesh Krishna; Aurko Roy; Mohit Iyyer; | naacl | 2021-05-23 |
| 274 | CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions Over Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take visual understanding to a higher level where systems are challenged to answer questions that involve mentally simulating the hypothetical consequences of performing specific actions in a given scenario. |
Shailaja Keyur Sampat; Akshay Kumar; Yezhou Yang; Chitta Baral; | naacl | 2021-05-23 |
| 275 | If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. |
Vikas Yadav; Steven Bethard; Mihai Surdeanu; | naacl | 2021-05-23 |
| 276 | DeCEMBERT: Learning from Noisy Instructional Videos Via Dense Captions and Entropy Minimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose an improved video-and-language pre-training method that first adds automatically-extracted dense region captions from the video frames as auxiliary text input, to provide informative visual cues for learning better video and language associations. |
Zineng Tang; Jie Lei; Mohit Bansal; | naacl | 2021-05-23 |
| 277 | Unsupervised Multi-hop Question Answering By Question Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose MQA-QG, an unsupervised framework that can generate human-like multi-hop training data from both homogeneous and heterogeneous data sources. |
Liangming Pan; Wenhu Chen; Wenhan Xiong; Min-Yen Kan; William Yang Wang; | naacl | 2021-05-23 |
| 278 | SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we first present a gradient-based interpretability approach to determine the questions most strongly correlated with the reasoning question on an image, and use this to evaluate VQA models on their ability to identify the relevant sub-questions needed to answer a reasoning question. |
Sameer Dharur; Purva Tendulkar; Dhruv Batra; Devi Parikh; Ramprasaath R. Selvaraju; | naacl | 2021-05-23 |
| 279 | D2S: Document-to-Slide Generation Via Query-Based Text Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years’ NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a two-step approach: |
Edward Sun; Yufang Hou; Dakuo Wang; Yunfeng Zhang; Nancy X. R. Wang; | naacl | 2021-05-23 |
| 280 | Distantly Supervised Transformers For E-Commerce Product QA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a practical instant question answering (QA) system on product pages of e-commerce services, where for each user query, relevant community question answer (CQA) pairs are retrieved. |
Happy Mittal; Aniket Chakrabarti; Belhassen Bayar; Animesh Anant Sharma; Nikhil Rasiwasia; | naacl | 2021-05-23 |
| 281 | Towards Few-shot Fact-Checking Via Perplexity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new way of utilizing the powerful transfer learning ability of a language model via a perplexity score. |
Nayeon Lee; Yejin Bang; Andrea Madotto; Pascale Fung; | naacl | 2021-05-23 |
| 282 | Self-Supervised Test-Time Learning for Reading Comprehension Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the task of unsupervised reading comprehension and present a method that performs test-time learning (TTL) on a given context (text passage), without requiring training on large-scale human-authored datasets containing context-question-answer triplets. |
Pratyay Banerjee; Tejas Gokhale; Chitta Baral; | naacl | 2021-05-23 |
| 283 | Video Question Answering with Phrases Via Semantic Roles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage semantic roles derived from video descriptions to mask out certain phrases, to introduce VidQAP which poses VidQA as a fill-in-the-phrase task. |
Arka Sadhu; Kan Chen; Ram Nevatia; | naacl | 2021-05-23 |
| 284 | KPQA: A Metric for Generative Question Answering Using Keyphrase Weights Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, we propose KPQA metric, a new metric for evaluating the correctness of GenQA. |
HWANHEE LEE et. al. | naacl | 2021-05-23 |
| 285 | Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. |
Hossein Rajaby Faghihi; Parisa Kordjamshidi; | naacl | 2021-05-23 |
| 286 | Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. |
Chen Zhao; Chenyan Xiong; Jordan Boyd-Graber; Hal Daum� III; | naacl | 2021-05-23 |
| 287 | MM-AVS: A Full-Scale Dataset for Multi-modal Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we release a full-scale multimodal dataset comprehensively gathering documents, summaries, images, captions, videos, audios, transcripts, and titles in English from CNN and Daily Mail. |
Xiyan Fu; Jun Wang; Zhenglu Yang; | naacl | 2021-05-23 |
| 288 | X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose X-METRA-ADA, a cross-lingual MEta-TRAnsfer learning ADAptation approach for NLU. |
MERYEM M�HAMDI et. al. | naacl | 2021-05-23 |
| 289 | Automatic Generation of Contrast Sets from Scene Graphs: Probing The Compositional Consistency of GQA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: While most contrast sets were created manually, requiring intensive annotation effort, we present a novel method which leverages rich semantic input representation to automatically generate contrast sets for the visual question answering task. |
Yonatan Bitton; Gabriel Stanovsky; Roy Schwartz; Michael Elhadad; | naacl | 2021-05-23 |
| 290 | DAGN: Discourse-Aware Graph Network for Logical Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore aggregating passage-level clues for solving logical reasoning QA by using discourse-based information. |
Yinya Huang; Meng Fang; Yu Cao; Liwei Wang; Xiaodan Liang; | naacl | 2021-05-23 |
| 291 | XOR QA: Cross-lingual Open-Retrieval Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this dataset, we introduce a task framework, called Cross-lingual Open-Retrieval Question Answering (XOR QA), that consists of three new tasks involving cross-lingual document retrieval from multilingual and English resources. |
AKARI ASAI et. al. | naacl | 2021-05-23 |
| 292 | Text Modular Networks: Learning to Decompose Tasks in The Language of Existing Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general framework called Text Modular Networks(TMNs) for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvable by existing models. |
Tushar Khot; Daniel Khashabi; Kyle Richardson; Peter Clark; Ashish Sabharwal; | naacl | 2021-05-23 |
| 293 | Game-theoretic Vocabulary Selection Via The Shapley Value and Banzhaf Index Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a vocabulary selection method that views words as members of a team trying to maximize the model’s performance. |
Roma Patel; Marta Garnelo; Ian Gemp; Chris Dyer; Yoram Bachrach; | naacl | 2021-05-23 |
| 294 | AVA: An Automatic EValuation Approach for Question Answering Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce AVA, an automatic evaluation approach for Question Answering, which given a set of questions associated with Gold Standard answers (references), can estimate system Accuracy. |
Thuy Vu; Alessandro Moschitti; | naacl | 2021-05-23 |
| 295 | ReadTwice: Reading Very Large Documents with Memories Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose ReadTwice, a simple and effective technique that combines several strengths of prior approaches to model long-range dependencies with Transformers. |
YURY ZEMLYANSKIY et. al. | naacl | 2021-05-23 |
| 296 | SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). |
Roshanak Mirzaee; Hossein Rajaby Faghihi; Qiang Ning; Parisa Kordjamshidi; | naacl | 2021-05-23 |
| 297 | Explainable Multi-hop Verbal Reasoning Through Internal Monologue Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Explainable multi-hop Verbal Reasoner (EVR) to solve these limitations by (a) decomposing multi-hop reasoning problems into several simple ones, and (b) using natural language to guide the intermediate reasoning hops. |
Zhengzhong Liang; Steven Bethard; Mihai Surdeanu; | naacl | 2021-05-23 |
| 298 | SPARTA: Efficient Open-Domain Question Answering Via Sparse Transformer Matching Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. |
Tiancheng Zhao; Xiaopeng Lu; Kyusong Lee; | naacl | 2021-05-23 |
| 299 | Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we use the multiple-choice reading comprehension (MCRC) and checking factual correctness of textual summarization (CFCS) tasks to investigate potential reasons for this. |
ANSHUMAN MISHRA et. al. | naacl | 2021-05-23 |
| 300 | EaSe: A Diagnostic Tool for VQA Based on Answer Diversity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose EASE, a simple diagnostic tool for Visual Question Answering (VQA) which quantifies the difficulty of an image, question sample. |
Shailza Jolly; Sandro Pezzelle; Moin Nabi; | naacl | 2021-05-23 |
| 301 | Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering Over Knowledge Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we exploit unsupervised bilingual lexicon induction (BLI) to map training questions in source language into those in target language as augmented training data, which circumvents language inconsistency between training and inference. |
Yucheng Zhou; Xiubo Geng; Tao Shen; Wenqiang Zhang; Daxin Jiang; | naacl | 2021-05-23 |
| 302 | Breadth First Reasoning Graph for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel model of Breadth First Reasoning Graph (BFR-Graph), which presents a new message passing way that better conforms to the reasoning process. |
Yongjie Huang; Meng Yang; | naacl | 2021-05-23 |
| 303 | A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore present Qasper, a dataset of 5049 questions over 1585 Natural Language Processing papers. |
PRADEEP DASIGI et. al. | naacl | 2021-05-23 |
| 304 | Worldly Wise (WoW) – Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards these ends, we present a new task and a synthetically-generated dataset to do Fact-based Visual Spoken-Question Answering (FVSQA). |
Kiran Ramnath; Leda Sari; Mark Hasegawa-Johnson; Chang Yoo; | naacl | 2021-05-23 |
| 305 | RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. |
YINGQI QU et. al. | naacl | 2021-05-23 |
| 306 | KILT: A Benchmark for Knowledge Intensive Language Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To catalyze research on models that condition on specific information in large textual resources, we present a benchmark for knowledge-intensive language tasks (KILT). |
FABIO PETRONI et. al. | naacl | 2021-05-23 |
| 307 | ASQ: Automatically Generating Question-Answer Pairs Using AMRs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce ASQ, a tool to automatically mine questions and answers from a sentence, using its Abstract Meaning Representation (AMR). |
Geetanjali Rakshit; Jeffrey Flanigan; | arxiv-cs.CL | 2021-05-20 |
| 308 | Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss the problem of geographic question answering (GeoQA). |
Gengchen Mai; Krzysztof Janowicz; Rui Zhu; Ling Cai; Ni Lao; | arxiv-cs.CL | 2021-05-19 |
| 309 | Multiple Meta-model Quantifying for Medical Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new multiple meta-model quantifying method that effectively learns meta-annotation and leverages meaningful features to the medical VQA task. |
TUONG DO et. al. | arxiv-cs.CV | 2021-05-19 |
| 310 | Representation Learning in Sequence to Sequence Tasks: Multi-filter Gaussian Mixture Autoencoder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a model to resolve the heterogeneity in the sequence to sequence task. |
Yunhao Yang; Zhaokun Xue; | arxiv-cs.CL | 2021-05-18 |
| 311 | NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. |
Junbin Xiao; Xindi Shang; Angela Yao; Tat-Seng Chua; | arxiv-cs.CV | 2021-05-18 |
| 312 | SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose SGD-QA, a simple and extensible model for schema-guided dialogue state tracking based on a question answering approach. |
Yang Zhang; Vahid Noroozi; Evelina Bakhturina; Boris Ginsburg; | arxiv-cs.CL | 2021-05-17 |
| 313 | Mining Architecture Tactics and Quality Attributes Knowledge in Stack Overflow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Objective: Using Stack Overflow (SO) as our source, our main goals are to effectively mine such knowledge; and to have some sense of how developers use ATs with respect to QA concerns from related discussions. |
Tingting Bi; Peng Liang; Antony Tang; Xin Xia; | arxiv-cs.SE | 2021-05-17 |
| 314 | Co-Attentional Transformers for Story-Based Video Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel co-attentional transformer model to better capture long-term dependencies seen in visual stories such as dramas and measure its performance on the video question answering task. |
B. Bebensee; B. -T. Zhang; | icassp | 2021-05-16 |
| 315 | Knowledge Distillation for Improved Accuracy in Spoken Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, the recent work shows that ASR systems generate highly noisy transcripts, which critically limit the capability of machine comprehension on the SQA task. To address the issue, we present a novel distillation framework. |
C. You; N. Chen; Y. Zou; | icassp | 2021-05-16 |
| 316 | Language Model Is All You Need: Natural Language Understanding As Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study the use of a certain family of transfer learning, where the target domain is mapped to the source domain. |
M. Namazifar; A. Papangelis; G. Tur; D. Hakkani-T�r; | icassp | 2021-05-16 |
| 317 | MCR-NET: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we propose a Multi-Step Co-Interactive Relation Network (MCR-Net) to explicitly model the mutual interaction and locate key clues from coarse to fine by introducing a co-interactive relation module. |
W. Peng; et al. | icassp | 2021-05-16 |
| 318 | Generating Natural Questions from Images for Multimodal Assistants IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an approach for generating diverse and meaningful questions that consider image content and metadata of image (e.g., location, associated keyword). |
A. Patel; A. Bindal; H. Kotek; C. Klein; J. Williams; | icassp | 2021-05-16 |
| 319 | Role Aware Multi-Party Dialogue Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In a novel aspect, this paper proposes the Role Aware Multi-Party Network (RAMPNet), a model utilizing the information of speaker and role to present who is speaking and who is mentioned, making role awareness an available message for our model. |
J. -H. HSU et. al. | icassp | 2021-05-16 |
| 320 | Integrating Subgraph-Aware Relation and Direction Reasoning for Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose a novel neural model, Relation-updated Direction-guided Answer Selector (RDAS), which converts relations in each subgraph to additional nodes to learn structure information. |
X. Wang; et al. | icassp | 2021-05-16 |
| 321 | Survey of Visual-Semantic Embedding Methods for Zero-Shot Image Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on zero-shot image retrieval using sentences as queries and present a survey of the technological trends in this area. |
Kazuya Ueki; | arxiv-cs.CV | 2021-05-16 |
| 322 | Adaptive Re-Balancing Network with Gate Mechanism for Long-Tailed Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose a unified Adaptive Re-balancing Network (ARN) to take care of classification in both head and tail classes, exhaustively improving performance for VQA. |
H. Chen; R. Liu; H. Fang; X. Zhang; | icassp | 2021-05-16 |
| 323 | Reinforcement Stacked Learning with Semantic-Associated Attention for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, depending on these problems, a semantic-associated attention method and a reinforcement stacked learning mechanism are proposed. |
X. Xiao; C. Zhang; S. Xiang; C. Pan; | icassp | 2021-05-16 |
| 324 | Coarse-To-Careful: Seeking Semantic-Related Knowledge for Open-Domain Commonsense Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards the issue of introducing related knowledge, we propose a semantic-driven knowledge-aware QA framework, which controls the knowledge injection in a coarse-to-careful fashion. |
L. Xing; Y. Hu; J. Yu; Y. Xie; W. Peng; | icassp | 2021-05-16 |
| 325 | Show Why The Answer Is Correct! Towards Explainable AI Using Compositional Temporal Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To minimize the black-box effect of these models and also to make them better exploit compositionality, we propose a Dynamic Neural Network (DMN), which can understand a particular question and then dynamically assemble various relatively shallow deep learning modules from a pool of modules to form a network. |
Nihar Bendre; Kevin Desai; Peyman Najafirad; | arxiv-cs.CV | 2021-05-15 |
| 326 | QAConv: Question Answering on Informative Conversations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source. |
Chien-Sheng Wu; Andrea Madotto; Wenhao Liu; Pascale Fung; Caiming Xiong; | arxiv-cs.CL | 2021-05-14 |
| 327 | Relation-aware Hierarchical Attention Framework for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a novel Relation-aware Hierarchical Attention (RHA) framework to learn both the static and dynamic relations of the objects in videos. |
FANGTAO LI et. al. | arxiv-cs.CV | 2021-05-13 |
| 328 | Encoding Explanatory Knowledge for Zero-shot Science Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes N-XKT (Neural encoding based on eXplanatory Knowledge Transfer), a novel method for the automatic transfer of explanatory knowledge through neural encoding mechanisms. |
Zili Zhou; Marco Valentino; Donal Landers; Andre Freitas; | arxiv-cs.CL | 2021-05-12 |
| 329 | Building A Question and Answer System for News Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We have built a span-based model using an Attention mechanism, where the model predicts the answer to a question as to the position of the start and end tokens in a paragraph. |
SANDIPAN BASU et. al. | arxiv-cs.CL | 2021-05-12 |
| 330 | Reinforcement Learning from Reformulations in Conversational Question Answering Over Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a step towards a more natural learning paradigm – from noisy and implicit feedback via question reformulations. |
Magdalena Kaiser; Rishiraj Saha Roy; Gerhard Weikum; | arxiv-cs.IR | 2021-05-11 |
| 331 | Found A Reason for Me? Weakly-supervised Grounded Visual Question Answering Using Capsules Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on a more relaxed setting: the grounding of relevant visual entities in a weakly supervised manner by training on the VQA task alone. |
AISHA UROOJ KHAN et. al. | arxiv-cs.CV | 2021-05-11 |
| 332 | Cross-Modal Generative Augmentation for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a generative model for data augmentation by leveraging the correlations among multiple modalities. |
Zixu Wang; Yishu Miao; Lucia Specia; | arxiv-cs.CV | 2021-05-11 |
| 333 | Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this survey, we mainly focus on the deep learning-based dialogue systems. |
JINJIE NI et. al. | arxiv-cs.CL | 2021-05-10 |
| 334 | Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we release the Longformer-based pre-trained language model, named as Lawformer, for Chinese legal long documents understanding. |
Chaojun Xiao; Xueyu Hu; Zhiyuan Liu; Cunchao Tu; Maosong Sun; | arxiv-cs.CL | 2021-05-09 |
| 335 | $\partial$-Explainer: Abductive Natural Language Inference Via Differentiable Convex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel framework named $\partial$-Explainer (Diff-Explainer) that combines the best of both worlds by casting the constrained optimization as part of a deep neural network via differentiable convex optimization and fine-tuning pre-trained transformers for downstream explainable NLP tasks. |
Mokanarangan Thayaparan; Marco Valentino; Deborah Ferreira; Julia Rozanova; André Freitas; | arxiv-cs.CL | 2021-05-07 |
| 336 | A Generative Symbolic Model for More General Natural Language Understanding and Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new fully-symbolic Bayesian model of semantic parsing and reasoning which we hope to be the first step in a research program toward more domain- and task-general NLU and AI. |
Abulhair Saparov; Tom M. Mitchell; | arxiv-cs.CL | 2021-05-06 |
| 337 | AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by this, in this work, we attempt to tackle the language prior problem from the viewpoint of the feature space learning. |
YANGYANG GUO et. al. | arxiv-cs.CV | 2021-05-05 |
| 338 | Proposal-free One-stage Referring Expression Via Grid-Word Cross-Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a proposal-free one-stage (PFOS) model that is able to regress the region-of-interest from the image, based on a textual query, in an end-to-end manner. |
Wei Suo; Mengyang Sun; Peng Wang; Qi Wu; | arxiv-cs.CV | 2021-05-05 |
| 339 | Rethinking Search: Making Domain Experts Out of Dilettantes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper examines how ideas from classical information retrieval and pre-trained language models can be synthesized and evolved into systems that truly deliver on the promise of domain expert advice. |
Donald Metzler; Yi Tay; Dara Bahri; Marc Najork; | arxiv-cs.IR | 2021-05-05 |
| 340 | How Do Developers Discuss and Support New Programming Languages in Technical Q&A Site? An Empirical Study of Go, Swift, and Rust in Stack Overflow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we have formally studied the discussions on three popular new languages introduced after the inception of SO (2008) and match those with the relevant activities in GitHub whenever appropriate. |
Partha Chakraborty; Rifat Shahriyar; Anindya Iqbal; Gias Uddin; | arxiv-cs.SE | 2021-05-04 |
| 341 | Iterated Learning for Emergent Systematicity in VQA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to address this problem using iterated learning, a cognitive science theory of the emergence of compositional languages in nature that has primarily been applied to simple referential games in machine learning. |
Ankit Vani; Max Schwarzer; Yuchen Lu; Eeshan Dhekane; Aaron Courville; | arxiv-cs.LG | 2021-05-03 |
| 342 | Quality Assurance Challenges for Machine Learning Software Applications During Software Development Life Cycle Phases Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper conducts an in-depth literature review of a large volume of research papers that focused on the quality assurance of ML models. |
Md Abdullah Al Alamin; Gias Uddin; | arxiv-cs.SE | 2021-05-03 |
| 343 | Semantic Modeling for Food Recommendation Explanations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the Food Explanation Ontology (FEO) that provides a formalism for modeling explanations to users for food-related recommendations. |
Ishita Padhiar; Oshani Seneviratne; Shruthi Chari; Daniel Gruen; Deborah L. McGuinness; | arxiv-cs.AI | 2021-05-03 |
| 344 | A Survey on VQA_Datasets and Approaches Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper will review and analyze existing datasets, metrics, and models proposed for the VQA task. |
Yeyun Zou; Qiyu Xie; | arxiv-cs.CV | 2021-05-02 |
| 345 | When to Fold’em: How to Answer Unanswerable Questions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present 3 different question-answering models trained on the SQuAD2.0 dataset — BIDAF, DocumentQA and ALBERT Retro-Reader — demonstrating the improvement of language models in the past three years. |
Marshall Ho; Zhipeng Zhou; Judith He; | arxiv-cs.CL | 2021-05-01 |
| 346 | Hidden Backdoors in Human-Centric Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we create covert and natural triggers for textual backdoor attacks, \textit{hidden backdoors}, where triggers can fool both modern language models and human inspection. |
SHAOFENG LI et. al. | arxiv-cs.CL | 2021-05-01 |
| 347 | Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Due to the severe lack of labeled data, existing methods of medical visual question answering usually rely on transfer learning to obtain effective image feature representation … |
Haifan Gong; Guanqi Chen; Sishuo Liu; Yizhou Yu; Guanbin Li; | arxiv-cs.MM | 2021-04-30 |
| 348 | Chop Chop BERT: Visual Question Answering By Chopping VisualBERT’s Heads Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To investigate why and how these models work on VQA so well, in this paper we explore the roles of individual heads and layers in Transformer models when handling $12$ different types of questions. |
Chenyu Gao; Qi Zhu; Peng Wang; Qi Wu; | arxiv-cs.CV | 2021-04-29 |
| 349 | Bio-SODA: Enabling Natural Language Question Answering Over Knowledge Graphs Without Training Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the challenges of natural language processing over knowledge graphs of scientific datasets. |
ANA CLAUDIA SIMA et. al. | arxiv-cs.DB | 2021-04-28 |
| 350 | Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, we propose question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process. |
Xinmeng Li; Mamoun Alazab; Qian Li; Keping Yu; Quanjun Yin; | arxiv-cs.CL | 2021-04-27 |
| 351 | Document Collection Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task. |
Rubèn Tito; Dimosthenis Karatzas; Ernest Valveny; | arxiv-cs.IR | 2021-04-27 |
| 352 | MDETR — Modulated Detection for End-to-End Multi-Modal Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose MDETR, an end-to-end modulated detector that detects objects in an image conditioned on a raw text query, like a caption or a question. |
AISHWARYA KAMATH et. al. | arxiv-cs.CV | 2021-04-26 |
| 353 | Document Structure Aware Relational Graph Convolutional Networks for Ontology Population Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by ideas from hypernym discovery and explainability, our method performs about 15 points more accurate than a stand-alone R-GCN model for this task. |
Abhay M Shalghar; Ayush Kumar; Balaji Ganesan; Aswin Kannan; Shobha G; | arxiv-cs.AI | 2021-04-26 |
| 354 | InfographicVQA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore the automatic understanding of infographic images by using Visual Question Answering technique.To this end, we present InfographicVQA, a new dataset that comprises a diverse collection of infographics along with natural language questions and answers annotations. |
MINESH MATHEW et. al. | arxiv-cs.CV | 2021-04-26 |
| 355 | GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. |
Timo Möller; Julian Risch; Malte Pietsch; | arxiv-cs.CL | 2021-04-26 |
| 356 | Towards Knowledge Graphs Validation Through Weighted Knowledge Sources Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose and implement a validation approach that computes a confidence score for every triple and instance in a KG. |
Elwin Huaman; Amar Tauqeer; Geni Bushati; Anna Fensel; | arxiv-cs.DB | 2021-04-26 |
| 357 | PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present our practice on training large-scale autoregressive language models named PanGu-$\alpha$, with up to 200 billion parameters. To enhance the generalization ability of PanGu-$\alpha$, we collect 1.1TB high-quality Chinese data from a wide range of domains to pretrain the model. |
WEI ZENG et. al. | arxiv-cs.CL | 2021-04-26 |
| 358 | Ask & Explore: Grounded Question Answering for Curiosity-Driven Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formulate curiosity based on grounded question answering by encouraging the agent to ask questions about the environment and be curious when the answers to these questions change. |
Jivat Neet Kaur; Yiding Jiang; Paul Pu Liang; | arxiv-cs.LG | 2021-04-24 |
| 359 | RelTransformer: Balancing The Visual Relationship Detection from Local Context, Scene and Memory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, we propose a novel transformer-based framework, dubbed as RelTransformer, which performs relationship prediction using rich semantic features from multiple image levels. |
Jun Chen; Aniket Agarwal; Sherif Abdelkarim; Deyao Zhu; Mohamed Elhoseiny; | arxiv-cs.CV | 2021-04-24 |
| 360 | Playing Lottery Tickets with Vision and Language Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform the first empirical study to assess whether such trainable subnetworks also exist in pre-trained V+L models. |
ZHE GAN et. al. | arxiv-cs.CV | 2021-04-23 |
| 361 | BERT-CoQAC: BERT-based Conversational Question Answering in Context IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the research gap, in this paper, we explore how to integrate conversational history into the neural machine comprehension system. |
MUNAZZA ZAIB et. al. | arxiv-cs.CL | 2021-04-22 |
| 362 | CaSIE: Canonicalize and Informative Selection of The OpenIE System Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an end-to-end system which takes a target incomplete KB and documents as input. |
H. Xin; X. Lin; L. Chen; | icde | 2021-04-22 |
| 363 | Sattiy at SemEval-2021 Task 9: An Ensemble Solution for Statement Verification and Evidence Finding with Tables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we exploited ensemble models of pre-trained language models over tables, TaPas and TaBERT, for Task A and adjust the result based on some rules extracted for Task B. Finally, in the leaderboard, we attain the F1 scores of 0.8496 and 0.7732 in Task A for the 2-way and 3-way evaluation, respectively, and the F1 score of 0.4856 in Task B. |
XIAOYI RUAN et. al. | arxiv-cs.AI | 2021-04-21 |
| 364 | Towards Solving Multimodal Comprehension Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We verify our proposed hypothesis and propose an algorithm capable of modifying the given dataset to remove the bias elements. |
Pritish Sahu; Karan Sikka; Ajay Divakaran; | arxiv-cs.CL | 2021-04-20 |
| 365 | Efficient Retrieval Optimized Multi-task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Retrieval Optimized Multi-task (ROM) framework for jointly training self-supervised tasks, knowledge retrieval, and extractive question answering. |
Hengxin Fun; Sunil Gandhi; Sujith Ravi; | arxiv-cs.CL | 2021-04-20 |
| 366 | GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To support question answering on scene graphs, we propose GraphVQA, a language-guided graph neural network framework that translates and executes a natural language question as multiple iterations of message passing among graph nodes. |
Weixin Liang; Yanhao Jiang; Zixuan Liu; | arxiv-cs.CL | 2021-04-20 |
| 367 | ELECTRAMed: A New Pre-trained Language Representation Model for Biomedical NLP Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a pre-trained domain-specific language model, called ELECTRAMed, suited for the biomedical field. |
Giacomo Miolo; Giulio Mantoan; Carlotta Orsenigo; | arxiv-cs.CL | 2021-04-19 |
| 368 | X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose X-METRA-ADA, a cross-lingual MEta-TRAnsfer learning ADAptation approach for NLU. |
MERYEM M’HAMDI et. al. | arxiv-cs.CL | 2021-04-19 |
| 369 | On The Influence of Masking Policies in Intermediate Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we perform a large-scale empirical study to investigate the effect of various MLM policies in intermediate pre-training. |
QINYUAN YE et. al. | arxiv-cs.CL | 2021-04-18 |
| 370 | Contextualized Query Embeddings for Conversational Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, in this paper, we propose a single-stage design, which supports end-to-end training and low-latency inference. To aid in this goal, we create a synthetic dataset for CS to overcome the lack of training data and explore different training strategies using this dataset. |
Sheng-Chieh Lin; Jheng-Hong Yang; Jimmy Lin; | arxiv-cs.IR | 2021-04-18 |
| 371 | Simple and Efficient Ways to Improve REALM Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the finetuning of REALM on various QA tasks and explore the limits of various hyperparameter and supervision choices. |
Vidhisha Balachandran; Ashish Vaswani; Yulia Tsvetkov; Niki Parmar; | arxiv-cs.CL | 2021-04-18 |
| 372 | FedNLP: A Research Platform for Federated Learning in Natural Language Processing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To facilitate FL research in NLP, we present the FedNLP, a research platform for federated learning in NLP. |
BILL YUCHEN LIN et. al. | arxiv-cs.CL | 2021-04-18 |
| 373 | Generative Context Pair Selection for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a generative context selection model for multi-hop question answering that reasons about how the given question could have been generated given a context pair. |
DHEERU DUA et. al. | arxiv-cs.CL | 2021-04-18 |
| 374 | GooAQ: Open Question Answering with Diverse Answer Types Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present GooAQ, a large-scale dataset with a variety of answer types. |
DANIEL KHASHABI et. al. | arxiv-cs.CL | 2021-04-18 |
| 375 | Can NLI Models Verify QA Systems’ Predictions? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explore the use of natural language inference (NLI) as a way to achieve this goal, as NLI inherently requires the premise (document context) to contain all necessary information to support the hypothesis (proposed answer to the question). |
Jifan Chen; Eunsol Choi; Greg Durrett; | arxiv-cs.CL | 2021-04-18 |
| 376 | SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper explores how saliency explanations can be used to improve KG-augmented models’ performance. |
AARON CHAN et. al. | arxiv-cs.CL | 2021-04-18 |
| 377 | Case-based Reasoning for Natural Language Queries Over Knowledge Bases Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a neuro-symbolic CBR approach for question answering over large knowledge bases (CBR-KBQA). |
RAJARSHI DAS et. al. | arxiv-cs.CL | 2021-04-18 |
| 378 | Joint Passage Ranking for Diverse Multi-Answer Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce JPR, a joint passage retrieval model focusing on reranking. |
Sewon Min; Kenton Lee; Ming-Wei Chang; Kristina Toutanova; Hannaneh Hajishirzi; | arxiv-cs.CL | 2021-04-17 |
| 379 | A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a novel graph-guided retrieval method to model the relations among answers across conversation turns. |
Yongqi Li; Wenjie Li; Liqiang Nie; | arxiv-cs.CL | 2021-04-17 |
| 380 | Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate several answer selection, question generation, and filtering methods that form a synthetic adversarial data generation pipeline that takes human-generated adversarial samples and unannotated text to create synthetic question-answer pairs. |
MAX BARTOLO et. al. | arxiv-cs.CL | 2021-04-17 |
| 381 | Explaining Answers with Entailment Trees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by not just listing supporting textual evidence (rationales), but also showing how such evidence leads to the answer in a systematic way. |
BHAVANA DALVI et. al. | arxiv-cs.CL | 2021-04-17 |
| 382 | Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Mobile app Tasks with Iterative Feedback (MoTIF), a dataset with natural language commands for the greatest number of interactive environments to date. |
ANDREA BURNS et. al. | arxiv-cs.CL | 2021-04-17 |
| 383 | MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we improve multilingual text-to-text transfer Transformer with translation pairs (mT6). |
ZEWEN CHI et. al. | arxiv-cs.CL | 2021-04-17 |
| 384 | ASBERT: Siamese and Triplet Network Embedding for Open Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present ASBERT, a framework built on the BERT architecture that employs Siamese and Triplet neural networks to learn an encoding function that maps a text to a fixed-size vector in an embedded space. |
Olabanji Shonibare; | arxiv-cs.IR | 2021-04-17 |
| 385 | Multi-Perspective Abstractive Answer Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces a novel dataset creation method to automatically create multi-perspective, bullet-point abstractive summaries from an existing CQA forum. |
Alexander R. Fabbri; Xiaojian Wu; Srini Iyer; Mona Diab; | arxiv-cs.CL | 2021-04-17 |
| 386 | $Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues Via Question Generation and Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by recent work on evaluating factual consistency in abstractive summarization (Durmus et al., 2020; Wang et al., 2020), we propose an automatic evaluation metric for factual consistency in knowledge-grounded dialogue models using automatic question generation and question answering. |
OR HONOVICH et. al. | arxiv-cs.CL | 2021-04-16 |
| 387 | IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce IndoNLG, the first such benchmark for the Indonesian language for natural language generation (NLG). We provide a vast and clean pre-training corpus of Indonesian, Sundanese, and Javanese datasets called Indo4B-Plus, which is used to train our pre-trained NLG model, IndoBART. |
SAMUEL CAHYAWIJAYA et. al. | arxiv-cs.CL | 2021-04-16 |
| 388 | What to Pre-Train On? Efficient Intermediate Task Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our best methods achieve an average Regret@3 of less than 1% across all target tasks, demonstrating that we are able to efficiently identify the best datasets for intermediate training. |
Clifton Poth; Jonas Pfeiffer; Andreas Rücklé; Iryna Gurevych; | arxiv-cs.CL | 2021-04-16 |
| 389 | VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by recent NMN approaches on image-grounded tasks, we introduce Video-grounded Neural Module Network (VGNMN) to model the information retrieval process in video-grounded language tasks as a pipeline of neural modules. |
Hung Le; Nancy F. Chen; Steven C. H. Hoi; | arxiv-cs.CV | 2021-04-16 |
| 390 | ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To facilitate these tasks, we introduce ESTER, a comprehensive machine reading comprehension (MRC) dataset for Event Semantic Relation Reasoning. |
RUJUN HAN et. al. | arxiv-cs.CL | 2021-04-16 |
| 391 | Cross-Modal Retrieval Augmentation for Multi-Modal Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we explore the use of unstructured external knowledge sources of images and their corresponding captions for improving visual question answering (VQA). |
SHIR GUR et. al. | arxiv-cs.CV | 2021-04-16 |
| 392 | Editing Factual Knowledge in Language Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present KnowledgeEditor, a method that can be used to edit this knowledge and, thus, fix ‘bugs’ or unexpected predictions without the need for expensive re-training or fine-tuning. |
Nicola De Cao; Wilker Aziz; Ivan Titov; | arxiv-cs.CL | 2021-04-16 |
| 393 | Are Multilingual BERT Models Robust? A Case Study on Adversarial Attacks for Multilingual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we are the first to explore and successfully attack a multilingual QA (MLQA) system pre-trained on multilingual BERT using several attack strategies for the adversarial statement reducing performance by as much as 85%. |
Sara Rosenthal; Mihaela Bornea; Avirup Sil; | arxiv-cs.CL | 2021-04-15 |
| 394 | Retrieval Augmentation Reduces Hallucination in Conversation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we explore the use of neural-retrieval-in-the-loop architectures – recently shown to be effective in open-domain QA (Lewis et al., 2020b; Izacard and Grave, 2020) – for knowledge-grounded dialogue, a task that is arguably more challenging as it requires querying based on complex multi-turn dialogue context and generating conversationally coherent responses. |
Kurt Shuster; Spencer Poff; Moya Chen; Douwe Kiela; Jason Weston; | arxiv-cs.CL | 2021-04-15 |
| 395 | Towards Deconfounding The Influence of Subject’s Demographic Characteristics in Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, robust QA evaluation is critical, and metrics should indicate how models will answer any question. |
Maharshi Gor; Kellie Webster; Jordan Boyd-Graber; | arxiv-cs.CL | 2021-04-15 |
| 396 | Data-QuestEval: A Referenceless Metric for Data to Text Semantic Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how QuestEval, which is a Text-vs-Text metric, can be adapted for the evaluation of Data-to-Text Generation systems. |
CLÉMENT REBUFFEL et. al. | arxiv-cs.CL | 2021-04-15 |
| 397 | Designing A Minimal Retrieve-and-Read System for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we discuss several orthogonal strategies to drastically reduce the footprint of a retrieve-and-read open-domain QA system by up to 160x. |
Sohee Yang; Minjoon Seo; | arxiv-cs.CL | 2021-04-15 |
| 398 | UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We solve this task by two approaches, Named Entity Recognition with spaCy library and Question-Answering with RoBERTa combining with ToxicBERT, and the former gains the highest F1-score of 66.99%. |
Phu Gia Hoang; Luan Thanh Nguyen; Kiet Van Nguyen; | arxiv-cs.CL | 2021-04-15 |
| 399 | Sequence Tagging for Biomedical Extractive Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the difference of the question distribution across the general and biomedical domains and discover biomedical questions are more likely to require list-type answers (multiple answers) than factoid-type answers (single answer). |
Wonjin Yoon; Richard Jackson; Jaewoo Kang; Aron Lagerberg; | arxiv-cs.CL | 2021-04-15 |
| 400 | TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering Over Relation Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose TransferNet, an effective and transparent model for multi-hop QA, which supports both label and text relations in a unified framework. |
Jiaxin Shi; Shulin Cao; Lei Hou; Juanzi Li; Hanwang Zhang; | arxiv-cs.CL | 2021-04-15 |
| 401 | Multivalent Entailment Graphs for Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We make three contributions: (1) we reinterpret the Distributional Inclusion Hypothesis to model entailment between predicates of different valencies, like DEFEAT(Biden, Trump) entails WIN(Biden); (2) we actualize this theory by learning unsupervised Multivalent Entailment Graphs of open-domain predicates; and (3) we demonstrate the capabilities of these graphs on a novel question answering task. |
Nick McKenna; Liane Guillou; Mohammad Javad Hosseini; Sander Bijl de Vroe; Mark Steedman; | arxiv-cs.CL | 2021-04-15 |
| 402 | TWEAC: Transformer with Extendable QA Agent Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, we propose composing multiple QA agents within a meta-QA system. |
Gregor Geigle; Nils Reimers; Andreas Rücklé; Iryna Gurevych; | arxiv-cs.CL | 2021-04-14 |
| 403 | Web Question Answering with Neurosymbolic Program Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new technique based on program synthesis for extracting information from webpages. |
QIAOCHU CHEN et. al. | arxiv-cs.PL | 2021-04-14 |
| 404 | Event Detection As Question Answering with Entity Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a recent and under-researched paradigm for the task of event detection (ED) by casting it as a question-answering (QA) problem with the possibility of multiple answers and the support of entities. |
Emanuela Boros; Jose G. Moreno; Antoine Doucet; | arxiv-cs.CL | 2021-04-14 |
| 405 | Jointly Learning Truth-Conditional Denotations and Groundings Using Parallel Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a model that jointly learns the denotations of words together with their groundings using a truth-conditional semantics. |
Leon Bergen; Dzmitry Bahdanau; Timothy J. O’Donnell; | arxiv-cs.CL | 2021-04-14 |
| 406 | NPE: An FPGA-based Overlay Processor for Natural Language Processing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present NPE, an FPGA-based overlay processor that can efficiently execute a variety of NLP models. |
HAMZA KHAN et. al. | arxiv-cs.AR | 2021-04-13 |
| 407 | QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph neural networks. |
Michihiro Yasunaga; Hongyu Ren; Antoine Bosselut; Percy Liang; Jure Leskovec; | arxiv-cs.CL | 2021-04-13 |
| 408 | Neuro-Symbolic VQA: A Review from The Perspective of AGI Desiderata Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we look at neuro-symbolic (NS)approaches to visual question answering (VQA) from the perspective of AGI desiderata. |
Ian Berlot-Attwell; | arxiv-cs.LG | 2021-04-13 |
| 409 | Structural Analysis of An All-purpose Question Answering Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To better understand this phenomenon, we conduct a structural analysis of a new all-purpose question answering model that we introduce. |
Vincent Micheli; Quentin Heinrich; François Fleuret; Wacim Belblidia; | arxiv-cs.CL | 2021-04-13 |
| 410 | MultiModalQA: Complex Question Answering Over Text, Tables and Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present MultiModalQA(MMQA): a challenging question answering dataset that requires joint reasoning over text, tables and images. |
ALON TALMOR et. al. | arxiv-cs.CL | 2021-04-13 |
| 411 | Reproducible Builds: Increasing The Integrity of Software Supply Chains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present reproducible builds, an approach that can determine whether generated binaries correspond with their original source code. |
Chris Lamb; Stefano Zacchiroli; | arxiv-cs.SE | 2021-04-13 |
| 412 | What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine the behaviour of non-target heads, that is, the output of heads when given input that belongs to a different task than the one they were trained for. |
Mor Geva; Uri Katz; Aviv Ben-Arie; Jonathan Berant; | arxiv-cs.CL | 2021-04-13 |
| 413 | SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). |
Roshanak Mirzaee; Hossein Rajaby Faghihi; Qiang Ning; Parisa Kordjmashidi; | arxiv-cs.CL | 2021-04-12 |
| 414 | A Replication Study of Dense Passage Retriever Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a replication study of this work, starting with model checkpoints provided by the authors, but otherwise from an independent implementation in our group’s Pyserini IR toolkit and PyGaggle neural text ranking library. |
Xueguang Ma; Kai Sun; Ronak Pradeep; Jimmy Lin; | arxiv-cs.CL | 2021-04-12 |
| 415 | Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extensively investigate approaches to enhancing the answer selection model with external knowledge from knowledge graph (KG). |
YANG DENG et. al. | arxiv-cs.CL | 2021-04-12 |
| 416 | Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. |
Chen Zhao; Chenyan Xiong; Jordan Boyd-Graber; Hal Daumé III; | arxiv-cs.CL | 2021-04-12 |
| 417 | Innovative Bert-based Reranking Language Models for Speech Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In view of the above, this paper presents a novel instantiation of the BERT-based contextualized language models (LMs) for use in reranking of N-best hypotheses produced by automatic speech recognition (ASR). |
Shih-Hsuan Chiu; Berlin Chen; | arxiv-cs.CL | 2021-04-11 |
| 418 | Fast Linking of Mathematical Wikidata Entities in Wikipedia Articles Using Annotation Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present our approach to structure and speed up this process by supporting annotators with a system that suggests formula names and meanings of mathematical identifiers. |
Philipp Scharpf; Moritz Schubotz; Bela Gipp; | arxiv-cs.DL | 2021-04-11 |
| 419 | Object-Centric Representation Learning for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new query-guided representation framework to turn a video into an evolving relational graph of objects, whose features and interactions are dynamically and conditionally inferred. |
Long Hoang Dang; Thao Minh Le; Vuong Le; Truyen Tran; | arxiv-cs.CV | 2021-04-11 |
| 420 | Fill-in-the-blank As A Challenging Video Understanding Evaluation Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose fill-in-the-blanks as a video understanding evaluation framework that addresses these previous evaluation drawbacks, and more closely reflects real-life settings where no multiple choices are given. We introduce a novel dataset consisting of 28,000 videos and fill-in-the-blank tests. |
SANTIAGO CASTRO et. al. | arxiv-cs.CV | 2021-04-09 |
| 421 | Meta-tuning Language Models to Answer Prompts Better Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this weakness, we propose meta-tuning, which trains the model to specialize in answering prompts but still generalize to unseen tasks. |
Ruiqi Zhong; Kristy Lee; Zheng Zhang; Dan Klein; | arxiv-cs.CL | 2021-04-09 |
| 422 | UPB at SemEval-2021 Task 8: Extracting Semantic Information on Measurements As Multi-Turn Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We approached these challenges by first identifying the quantities, extracting their units of measurement, classifying them with corresponding modifiers, and afterwards using them to jointly solve the last three subtasks in a multi-turn question answering manner. |
Andrei-Marius Avram; George-Eduard Zaharia; Dumitru-Clementin Cercel; Mihai Dascalu; | arxiv-cs.CL | 2021-04-09 |
| 423 | TransWiC at SemEval-2021 Task 2: Transformer-based Multilingual and Cross-lingual Word-in-Context Disambiguation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite that, our best model achieves 0.90 accuracy for English-English subtask which is very compatible compared to the best result of the subtask; 0.93 accuracy. |
Hansi Hettiarachchi; Tharindu Ranasinghe; | arxiv-cs.CL | 2021-04-09 |
| 424 | A Question-answering Based Framework for Relation Extraction Validation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the possibility of using question answering as validation. |
Jiayang Cheng; Haiyun Jiang; Deqing Yang; Yanghua Xiao; | arxiv-cs.CL | 2021-04-07 |
| 425 | Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an evaluation methodology for visual question answering (VQA) to better diagnose cases of shortcut learning. |
Corentin Dancette; Remi Cadene; Damien Teney; Matthieu Cord; | arxiv-cs.CV | 2021-04-07 |
| 426 | Multimodal Continuous Visual Attention Mechanisms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new continuous attention mechanism that produces multimodal densities, in the form of mixtures of Gaussians. |
António Farinhas; André F. T. Martins; Pedro M. Q. Aguiar; | arxiv-cs.CV | 2021-04-07 |
| 427 | Compressing Visual-linguistic Model Via Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a small VL model. |
ZHIYUAN FANG et. al. | arxiv-cs.CV | 2021-04-05 |
| 428 | Paired Examples As Indirect Supervision in Latent Decision Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a way to leverage paired examples that provide stronger cues for learning latent decisions. |
Nitish Gupta; Sameer Singh; Matt Gardner; Dan Roth; | arxiv-cs.CL | 2021-04-04 |
| 429 | Conversational Question Answering Over Knowledge Graphs with Transformer and Graph Attention Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). |
ENDRI KACUPAJ et. al. | arxiv-cs.CL | 2021-04-04 |
| 430 | MMBERT: Multimodal BERT Pretraining for Improved Medical VQA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, we propose a solution inspired by self-supervised pretraining of Transformer-style architectures for NLP, Vision and Language tasks. |
YASH KHARE et. al. | arxiv-cs.CV | 2021-04-03 |
| 431 | ASPER: Attention-based Approach to Extract Syntactic Patterns Denoting Semantic Relations in Sentential Context Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an attention-based supervised deep learning model, ASPER, which extracts syntactic patterns between entities exhibiting a given semantic relation in the sentential context. |
Md. Ahsanul Kabir; Typer Phillips; Xiao Luo; Mohammad Al Hasan; | arxiv-cs.CL | 2021-04-03 |
| 432 | Using Simulation to Aid The Design and Optimization of Intelligent User Interfaces for Quality Assurance Processes in Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose using simulation to aid the design and optimization of intelligent user interfaces for QA4ML processes. |
YU ZHANG et. al. | arxiv-cs.HC | 2021-04-02 |
| 433 | Type Prediction Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we describe two systems aimed at predicting type information for the following two tasks, namely, a TypeSuggest module, an unsupervised system designed to predict types for a set of user-entered query terms, and an Answer Type prediction module, that provides a solution for the task of determining the correct type of the answer expected to a given query. |
Sarthak Dash; Nandana Mihindukulasooriya; Alfio Gliozzo; Mustafa Canim; | arxiv-cs.CL | 2021-04-02 |
| 434 | VisQA: X-raying Vision and Language Reasoning in Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present VisQA, a visual analytics tool that explores this question of reasoning vs. bias exploitation. |
THEO JAUNET et. al. | arxiv-cs.CV | 2021-04-02 |
| 435 | Limiting Tags Fosters Efficiency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we use information-theoretic measures to track the descriptive and retrieval efficiency of tags on Stack Overflow, a question-answering system that strictly limits the number of tags users can specify per question. |
Tiago Santos; Keith Burghardt; Kristina Lerman; Denis Helic; | arxiv-cs.CY | 2021-04-02 |
| 436 | Towards General Purpose Vision Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a task-agnostic vision-language system that accepts an image and a natural language task description and outputs bounding boxes, confidences, and text. |
Tanmay Gupta; Amita Kamath; Aniruddha Kembhavi; Derek Hoiem; | arxiv-cs.CV | 2021-04-01 |
| 437 | CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we first bring to light the sensitivity of pre-training objectives (contrastive vs. reconstructive) to domain discrepancy. |
Luowei Zhou; Jingjing Liu; Yu Cheng; Zhe Gan; Lei Zhang; | arxiv-cs.CV | 2021-04-01 |
| 438 | CURIE: An Iterative Querying Approach for Reasoning About Situations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method to iteratively build a graph of relevant consequences explicitly in a structured situational graph (st-graph) using natural language queries over a finetuned language model (M). |
DHEERAJ RAJAGOPAL et. al. | arxiv-cs.CL | 2021-04-01 |
| 439 | FeTaQA: Free-form Table Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues and to demonstrate the full challenge of table question answering, we introduce FeTaQA, a new dataset with 10K Wikipedia-based {table, question, free-form answer, supporting table cells} pairs. |
LINYONG NAN et. al. | arxiv-cs.CL | 2021-04-01 |
| 440 | An Investigation of Critical Issues in Bias Mitigation Techniques Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we introduce an improved evaluation protocol, sensible metrics, and a new dataset, which enables us to ask and answer critical questions about bias mitigation algorithms. We introduce a new dataset called Biased MNIST that enables assessment of robustness to multiple bias sources. |
Robik Shrestha; Kushal Kafle; Christopher Kanan; | arxiv-cs.LG | 2021-03-31 |
| 441 | Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose a novel neural model, Relation-updated Direction-guided Answer Selector (RDAS), which converts relations in each subgraph to additional nodes to learn structure information. |
XU WANG et. al. | arxiv-cs.CL | 2021-03-31 |
| 442 | SUTD-TrafficQA: A Question Answering Benchmark and An Efficient Network for Video Reasoning Over Traffic Events IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10,080 in-the-wild videos and annotated 62,535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios. |
Li Xu; He Huang; Jun Liu; | arxiv-cs.CV | 2021-03-29 |
| 443 | Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the first method to explain prediction by any Transformer-based architecture, including bi-modal Transformers and Transformers with co-attentions. |
Hila Chefer; Shir Gur; Lior Wolf; | arxiv-cs.CV | 2021-03-29 |
| 444 | InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, We propose InsertGNN, a simple yet effective model that represents the problem as a graph and adopts the graph Neural Network (GNN) to learn the connection between sentences. |
Fang Wu; Xiang Bai; | arxiv-cs.CL | 2021-03-28 |
| 445 | ‘Just Because You Are Right, Doesn’t Mean I Am Wrong’: Overcoming A Bottleneck in The Development and Evaluation of Open-Ended Visual Question Answering (VQA) Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Alternative Answer Sets (AAS) of ground-truth answers to address this limitation, which is created automatically using off-the-shelf NLP tools. |
MAN LUO et. al. | arxiv-cs.CL | 2021-03-27 |
| 446 | You Can Do Better! If You Elaborate The Reason When Making Prediction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a neural predictive approach to make a prediction and generate its corresponding explanation simultaneously. |
Dongfang Li; Jingcong Tao; Qingcai Chen; Baotian Hu; | arxiv-cs.CL | 2021-03-27 |
| 447 | Knowing What VQA Does Not: Pointing to Error-Inducing Regions to Improve Explanation Helpfulness IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence, we propose Error Maps that clarify the error by highlighting image regions where the model is prone to err. |
ARIJIT RAY et. al. | arxiv-cs.CV | 2021-03-26 |
| 448 | On The Hidden Treasure of Dialog in Video Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a new approach to understand the whole story without such external sources. |
Deniz Engin; Yannis Avrithis; Ngoc Q. K. Duong; François Schnitzler; | arxiv-cs.CV | 2021-03-26 |
| 449 | Visual Grounding Strategies for Text-Only Natural Language Processing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we leverage multimodal modeling for purely textual tasks (language modeling and classification) with the expectation that the multimodal pretraining provides a grounding that can improve text processing accuracy. |
Damien Sileo; | arxiv-cs.CL | 2021-03-25 |
| 450 | UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on A New Multitask Benchmark IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two new ways to evaluate commonsense models, emphasizing their generality on new tasks and building on diverse, recently introduced benchmarks. First, we propose a new multitask benchmark, RAINBOW, to promote research on commonsense models that generalize well over multiple tasks and datasets. |
Nicholas Lourie; Ronan Le Bras; Chandra Bhagavatula; Yejin Choi; | arxiv-cs.CL | 2021-03-24 |
| 451 | Complex Factoid Question Answering with A Free-Text Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce DELFT, a factoid question answering system which combines the nuance and depth of knowledge graph question answering approaches with the broader coverage of free-text. |
Chen Zhao; Chenyan Xiong; Xin Qian; Jordan Boyd-Graber; | arxiv-cs.CL | 2021-03-23 |
| 452 | QuestEval: Summarization Asks for Fact-based Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend previous approaches and propose a unified framework, named QuestEval. |
THOMAS SCIALOM et. al. | arxiv-cs.CL | 2021-03-23 |
| 453 | Complementary Evidence Identification in Open-Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new problem of complementary evidence identification for open-domain question answering (QA). |
XIANGYANG MOU et. al. | arxiv-cs.CL | 2021-03-22 |
| 454 | Mitigating False-Negative Contexts in Multi-document QuestionAnswering with Retrieval Marginalization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information from which the reasoning model can derive an answer. |
Ansong Ni; Matt Gardner; Pradeep Dasigi; | arxiv-cs.CL | 2021-03-22 |
| 455 | Multi-Modal Answer Validation for Knowledge-Based VQA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose Multi-modal Answer Validation using External knowledge (MAVEx), where the idea is to validate a set of promising answer candidates based on answer-specific knowledge retrieval. |
Jialin Wu; Jiasen Lu; Ashish Sabharwal; Roozbeh Mottaghi; | arxiv-cs.CV | 2021-03-22 |
| 456 | Open Domain Question Answering Over Tables Via Dense Retrieval IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a retriever designed to handle tabular context. |
Jonathan Herzig; Thomas Müller; Syrine Krichene; Julian Martin Eisenschlos; | arxiv-cs.CL | 2021-03-22 |
| 457 | How to Design Sample and Computationally Efficient VQA Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous models propose different methods for the vision and language tasks, but which ones perform the best while being sample and computationally efficient? |
KARAN SAMEL et. al. | arxiv-cs.LG | 2021-03-21 |
| 458 | Characterization and Prediction of Questions Without Accepted Answers on Stack Overflow IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate unresolved questions, without accepted answers, on Stack Overflow. |
Mohamad Yazdaninia; David Lo; Ashkan Sami; | arxiv-cs.SE | 2021-03-21 |
| 459 | Controllable Generation from Pre-trained Language Models Via Inverse Prompting IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this challenge, we propose an innovative method, inverse prompting, to better control text generation. |
XU ZOU et. al. | arxiv-cs.CL | 2021-03-19 |
| 460 | Attention-based Model for Predicting Question Relatedness on Stack Overflow IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we adopt the deep learning technique, propose an Attention-based Sentence pair Interaction Model (ASIM) to predict the relatedness between questions on Stack Overflow automatically. |
Jiayan Pei; Yimin Wu; Zishan Qin; Yao Cong; Jingtao Guan; | arxiv-cs.CL | 2021-03-19 |
| 461 | Towards Few-Shot Fact-Checking Via Perplexity IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new way of utilizing the powerful transfer learning ability of a language model via a perplexity score. Moreover, we construct and publicly release two new fact-checking datasets related to COVID-19. |
Nayeon Lee; Yejin Bang; Andrea Madotto; Madian Khabsa; Pascale Fung; | arxiv-cs.CL | 2021-03-17 |
| 462 | SILT: Efficient Transformer Training for Inter-lingual Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new architecture called Siamese Inter-Lingual Transformer (SILT), to efficiently align multilingual embeddings for Natural Language Inference, allowing for unmatched language pairs to be processed. |
Javier Huertas-Tato; Alejandro Martín; David Camacho; | arxiv-cs.CL | 2021-03-17 |
| 463 | A Multilingual African Embedding for FAQ Chatbots IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce an Artificial Intelligence Powered chatbot for crisis communication that would be omnichannel, multilingual and multi dialectal. |
Aymen Ben Elhaj Mabrouk; Moez Ben Haj Hmida; Chayma Fourati; Hatem Haddad; Abir Messaoudi; | arxiv-cs.CL | 2021-03-16 |
| 464 | Towards A Question Answering Assistant for Software Development Using A Transformer-based Language Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this preliminary study, we particularly investigate if a how-to question filter and the level of context in the question may impact the results of a question answering transformer-based model. |
Liliane do Nascimento Vale; Marcelo de Almeida Maia; | arxiv-cs.SE | 2021-03-16 |
| 465 | KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these challenges, we facilitate knowledge graphs and propose a novel entity synonyms discovery framework, named \emph{KGSynNet}. |
YIYING YANG et. al. | arxiv-cs.AI | 2021-03-16 |
| 466 | Context Transformer with Stacked Pointer Networks for Conversational Question Answering Over Knowledge Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel framework named CARTON, which performs multi-task semantic parsing for handling the problem of conversational question answering over a large-scale knowledge graph. |
Joan Plepi; Endri Kacupaj; Kuldeep Singh; Harsh Thakkar; Jens Lehmann; | arxiv-cs.CL | 2021-03-13 |
| 467 | ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents ParaQA, a question answering (QA) dataset with multiple paraphrased responses for single-turn conversation over knowledge graphs (KG). |
Endri Kacupaj; Barshana Banerjee; Kuldeep Singh; Jens Lehmann; | arxiv-cs.CL | 2021-03-13 |
| 468 | Cooperative Learning of Zero-Shot Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a cooperative, self-play learning framework, REGEX, for question generation and answering. |
Hongyin Luo; Shang-Wen Li; Seunghak Yu; James Glass; | arxiv-cs.CL | 2021-03-12 |
| 469 | Knowledge Graph Question Answering Using Graph-Pattern Isomorphism IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel QA approach, dubbed TeBaQA. |
DANIEL VOLLMERS et. al. | arxiv-cs.AI | 2021-03-11 |
| 470 | Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate conversational answer generation for QA. |
Stan Peshterliev; Barlas Oguz; Debojeet Chatterjee; Hakan Inan; Vikas Bhardwaj; | arxiv-cs.CL | 2021-03-11 |
| 471 | CANINE: Pre-training An Efficient Tokenization-Free Encoder for Language Representation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present CANINE, a neural encoder that operates directly on character sequences, without explicit tokenization or vocabulary, and a pre-training strategy that operates either directly on characters or optionally uses subwords as a soft inductive bias. |
Jonathan H. Clark; Dan Garrette; Iulia Turc; John Wieting; | arxiv-cs.CL | 2021-03-11 |
| 472 | RL-CSDia: Representation Learning of Computer Science Diagrams IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we construct a novel dataset of graphic diagrams named Computer Science Diagrams (CSDia). |
SHAOWEI WANG et. al. | arxiv-cs.CV | 2021-03-10 |
| 473 | MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we propose a Multi-Step Co-Interactive Relation Network (MCR-Net) to explicitly model the mutual interaction and locate key clues from coarse to fine by introducing a co-interactive relation module. |
WEI PENG et. al. | arxiv-cs.CL | 2021-03-08 |
| 474 | A Survey of Embodied AI: From Simulators to Research Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By benchmarking nine state-of-the-art embodied AI simulators in terms of seven features, this paper aims to understand the simulators in their provision for use in embodied AI research. |
Jiafei Duan; Samson Yu; Hui Li Tan; Hongyuan Zhu; Cheston Tan; | arxiv-cs.AI | 2021-03-08 |
| 475 | Contextual Dropout: An Efficient Sample-Dependent Dropout Module IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose contextual dropout with an efficient structural design as a simple and scalable sample-dependent dropout module, which can be applied to a wide range of models at the expense of only slightly increased memory and computational cost. |
Xinjie Fan; Shujian Zhang; Korawat Tanwisuth; Xiaoning Qian; Mingyuan Zhou; | arxiv-cs.LG | 2021-03-06 |
| 476 | AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We report some experiments for QA and QG that yield improvements on both tasks, and assess how they interact to produce a list of Q&A items for a text. |
Melissa Roemmele; Deep Sidhpura; Steve DeNeefe; Ling Tsou; |