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.
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 | Relation-aware Hierarchical Attention Framework for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Lacking understanding of the the dynamic relationships and interactions among objects brings a great challenge to VideoQA task.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 |
| 2 | 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 |
| 3 | 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 |
| 4 | 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 |
| 5 | 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 |
| 6 | 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 |
| 7 | 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. | arxiv-cs.CL | 2021-05-10 |
| 8 | 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. | arxiv-cs.CL | 2021-05-10 |
| 9 | 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. | arxiv-cs.CL | 2021-05-10 |
| 10 | Recent Advances in Deep Learning-based Dialogue Systems 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 |
| 11 | 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 |
| 12 | 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; | arxiv-cs.IR | 2021-05-09 |
| 13 | 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 on 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. | arxiv-cs.IR | 2021-05-08 |
| 14 | D2S: Document-to-Slide Generation Via Query-Based Text Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming … |
Edward Sun; Yufang Hou; Dakuo Wang; Yunfeng Zhang; Nancy X. R. Wang; | arxiv-cs.CL | 2021-05-08 |
| 15 | $\partial$-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 |
| 16 | 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; | arxiv-cs.CL | 2021-05-06 |
| 17 | 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 |
| 18 | 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 5,049 questions over 1,585 Natural Language Processing papers. |
PRADEEP DASIGI et. al. | arxiv-cs.CL | 2021-05-06 |
| 19 | 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 |
| 20 | Rethinking Search: Making 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 large pre-trained language models can be synthesized and evolved into systems that truly deliver on the promise of expert advice. |
Donald Metzler; Yi Tay; Dara Bahri; Marc Najork; | arxiv-cs.IR | 2021-05-05 |
| 21 | 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 |
| 22 | 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 |
| 23 | Iterated Learning for Emergent Systematicity in VQA 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 |
| 24 | 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 |
| 25 | 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 |
| 26 | 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 |
| 27 | 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 |
| 28 | 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 |
| 29 | 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 |
| 30 | 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 |
| 31 | 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; | arxiv-cs.CV | 2021-04-28 |
| 32 | 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 |
| 33 | 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 |
| 34 | 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 |
| 35 | 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 |
| 36 | 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 |
| 37 | 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 |
| 38 | 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 |
| 39 | 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 |
| 40 | 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 |
| 41 | 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 |
| 42 | 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 |
| 43 | BERT-CoQAC: BERT-based Conversational Question Answering in Context 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 |
| 44 | 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 |
| 45 | 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 |
| 46 | 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 |
| 47 | 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 |
| 48 | 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 |
| 49 | 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 |
| 50 | 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 |
| 51 | 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 |
| 52 | 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 |
| 53 | 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 |
| 54 | 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 |
| 55 | 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 |
| 56 | 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 |
| 57 | SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore whether KG explanations can be used as supervision for teaching these KG-augmented models how to filter out unhelpful KG information. |
AARON CHAN et. al. | arxiv-cs.CL | 2021-04-18 |
| 58 | 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 |
| 59 | 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 |
| 60 | 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 |
| 61 | 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 |
| 62 | 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 |
| 63 | 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 |
| 64 | 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 |
| 65 | 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 |
| 66 | 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 |
| 67 | $Q^{2}$: 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 |
| 68 | 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 |
| 69 | 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 |
| 70 | 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 |
| 71 | 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 |
| 72 | 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 |
| 73 | 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. | arxiv-cs.AI | 2021-04-16 |
| 74 | 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 |
| 75 | 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 |
| 76 | 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 |
| 77 | 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: This enables us to use pre-trained transformer-based language models on other QA benchmarks by adapting those to the procedural text understanding. |
Hossein Rajaby Faghihi; Parisa Kordjamshidi; | arxiv-cs.CL | 2021-04-15 |
| 78 | 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 |
| 79 | 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 |
| 80 | 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 |
| 81 | 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 |
| 82 | 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 |
| 83 | 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 |
| 84 | 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 |
| 85 | 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 |
| 86 | 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 |
| 87 | 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 |
| 88 | 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 |
| 89 | QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here 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-based message passing. |
Michihiro Yasunaga; Hongyu Ren; Antoine Bosselut; Percy Liang; Jure Leskovec; | arxiv-cs.CL | 2021-04-13 |
| 90 | 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; | arxiv-cs.CV | 2021-04-13 |
| 91 | 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 |
| 92 | 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 |
| 93 | 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 |
| 94 | NPE: An FPGA-based Overlay Processor for Natural Language Processing 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 |
| 95 | 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 |
| 96 | 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 |
| 97 | 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 |
| 98 | 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 |
| 99 | 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 |
| 100 | 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 |
| 101 | Innovative Bert-based Reranking Language Models for Speech Recognition 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 |
| 102 | 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 |
| 103 | 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 |
| 104 | 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 |
| 105 | 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 |
| 106 | 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 |
| 107 | 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 |
| 108 | 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. | arxiv-cs.CV | 2021-04-08 |
| 109 | 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; | arxiv-cs.CV | 2021-04-08 |
| 110 | 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; | arxiv-cs.CV | 2021-04-08 |
| 111 | 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 ecommerce 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; | arxiv-cs.LG | 2021-04-07 |
| 112 | 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 |
| 113 | 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 |
| 114 | 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 |
| 115 | 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 |
| 116 | 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 |
| 117 | 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 |
| 118 | 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 |
| 119 | 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 |
| 120 | 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 |
| 121 | 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 |
| 122 | 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 |
| 123 | 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 |
| 124 | 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 |
| 125 | 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 |
| 126 | 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 |
| 127 | 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 UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. |
MINGYANG ZHOU et. al. | arxiv-cs.CV | 2021-04-01 |
| 128 | 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 |
| 129 | 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 |
| 130 | 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 |
| 131 | Domain-robust VQA with Diverse Datasets and Methods But No Target Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To emulate the setting of real-world generalization, we focus on unsupervised domain adaptation and the open-ended classification task formulation. |
Mingda Zhang; Tristan Maidment; Ahmad Diab; Adriana Kovashka; Rebecca Hwa; | arxiv-cs.CV | 2021-03-29 |
| 132 | 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. We also provide a balanced subset of $3.9M$ question answer pairs, $3$ orders of magnitude larger than existing benchmarks, that minimizes bias by balancing the answer distributions and types of question structures. |
Madeleine Grunde-McLaughlin; Ranjay Krishna; Maneesh Agrawala; | arxiv-cs.CV | 2021-03-29 |
| 133 | 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 |
| 134 | TrafficQA: A Question Answering Benchmark and An Efficient Network for Video Reasoning Over Traffic Events Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we create a novel dataset, 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 |
| 135 | InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem? 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 |
| 136 | ‘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 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 |
| 137 | You Can Do Better! If You Elaborate The Reason When Making Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel neural predictive framework coupled with large pre-trained language models to make a prediction and generate its corresponding explanation simultaneously. |
Dongfang Li; Jingcong Tao; Qingcai Chen; Baotian Hu; | arxiv-cs.CL | 2021-03-27 |
| 138 | Knowing What VQA Does Not: Pointing to Error-Inducing Regions to Improve Explanation Helpfulness 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 |
| 139 | On The Hidden Treasure of Dialog in Video Question Answering 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 |
| 140 | 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; | arxiv-cs.CL | 2021-03-26 |
| 141 | Visual Grounding Strategies for Text-Only Natural Language Processing 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 |
| 142 | UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on A New Multitask Benchmark 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 |
| 143 | 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 |
| 144 | Complex Factoid Question Answering with A Free-Text Knowledge Graph 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 |
| 145 | Multi-Modal Answer Validation for Knowledge-Based VQA 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 |
| 146 | Mitigating False-Negative Contexts in Multi-document QuestionAnswering with Retrieval Marginalization 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 |
| 147 | Complementary Evidence Identification in Open-Domain Question Answering 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 |
| 148 | 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 Müller; Syrine Krichene; Julian Martin Eisenschlos; | arxiv-cs.CL | 2021-03-22 |
| 149 | Characterization and Prediction of Questions Without Accepted Answers on Stack Overflow 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 |
| 150 | How to Design Sample and Computationally Efficient VQA Models 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 |
| 151 | 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 \textit{context-question-answer} triplets. |
Pratyay Banerjee; Tejas Gokhale; Chitta Baral; | arxiv-cs.CL | 2021-03-20 |
| 152 | Attention-based Model for Predicting Question Relatedness on Stack Overflow 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 |
| 153 | Controllable Generation from Pre-trained Language Models Via Inverse Prompting 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 |
| 154 | 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. 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 |
| 155 | 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: Recent works have shown that supervised models often exploit data artifacts to achieve good test scores while their performance severely degrades on samples outside their training distribution. |
Yonatan Bitton; Gabriel Stanovsky; Roy Schwartz; Michael Elhadad; | arxiv-cs.CL | 2021-03-17 |
| 156 | SML: A New Semantic Embedding Alignment Transformer for Efficient Cross-lingual Natural Language Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new architecture, siamese multilingual transformer (SML), to efficiently align multilingual embeddings for Natural Language Inference. |
Javier Huertas-Tato; Alejandro Martín; David Camacho; | arxiv-cs.CL | 2021-03-17 |
| 157 | KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph 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 |
| 158 | A Multilingual African Embedding for FAQ Chatbots 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 |
| 159 | Towards A Question Answering Assistant for Software Development Using A Transformer-based Language Model 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 |
| 160 | ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation 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 |
| 161 | Context Transformer with Stacked Pointer Networks for Conversational Question Answering Over Knowledge Graphs 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 |
| 162 | Cooperative Learning of Zero-Shot Machine Reading Comprehension 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 |
| 163 | Knowledge Graph Question Answering Using Graph-Pattern Isomorphism 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 |
| 164 | CANINE: Pre-training An Efficient Tokenization-Free Encoder for Language Representation 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 |
| 165 | Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering 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 |
| 166 | Hurdles to Progress in Long-form Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide suggestions to mitigate each of these issues, which we hope will lead to more rigorous LFQA research and meaningful progress in the future. |
Kalpesh Krishna; Aurko Roy; Mohit Iyyer; | arxiv-cs.CL | 2021-03-10 |
| 167 | RL-CSDia: Representation Learning of Computer Science Diagrams 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 |
| 168 | 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. | arxiv-cs.CV | 2021-03-09 |
| 169 | MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension 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 |
| 170 | A Survey of Embodied AI: From Simulators to Research Tasks 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 |
| 171 | Contextual Dropout: An Efficient Sample-Dependent Dropout Module 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 |
| 172 | AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents 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; | arxiv-cs.CL | 2021-03-05 |
| 173 | Graph-Based Tri-Attention Network for Answer Ranking in CQA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the limitations, we devise a novel graph-based tri-attention network, namely GTAN, which has two innovations. |
WEI ZHANG et. al. | arxiv-cs.CL | 2021-03-05 |
| 174 | Advances in Multi-turn Dialogue Comprehension: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we review the previous methods from the perspective of dialogue modeling. |
Zhuosheng Zhang; Hai Zhao; | arxiv-cs.CL | 2021-03-04 |
| 175 | Visual Question Answering: Which Investigated Applications? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Some recent surveys about VQA approaches have focused on methods underlying either the image-related processing or the verbal-related one, or on the way to consistently fuse the conveyed information. |
Silvio Barra; Carmen Bisogni; Maria De Marsico; Stefano Ricciardi; | arxiv-cs.CV | 2021-03-04 |
| 176 | Weakly-Supervised Open-Retrieval Conversational Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we introduce a learned weak supervision approach that can identify a paraphrased span of the known answer in a passage. |
CHEN QU et. al. | arxiv-cs.IR | 2021-03-03 |
| 177 | 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. | arxiv-cs.IR | 2021-03-01 |
| 178 | Learning Reasoning Paths Over Semantic Graphs for Video-grounded Dialogues Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework of Reasoning Paths in Dialogue Context (PDC). |
Hung Le; Nancy F. Chen; Steven C. H. Hoi; | arxiv-cs.AI | 2021-03-01 |
| 179 | Natural Language Video Localization: A Revisit in Span-based Question Answering Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address the NLVL from a new perspective, i.e., span-based question answering (QA), by treating the input video as a text passage. |
HAO ZHANG et. al. | arxiv-cs.CL | 2021-02-26 |
| 180 | PharmKE: Knowledge Extraction Platform for Pharmaceutical Texts Using Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present PharmKE, a text analysis platform focused on the pharmaceutical domain, which applies deep learning through several stages for thorough semantic analysis of pharmaceutical articles. |
Nasi Jofche; Kostadin Mishev; Riste Stojanov; Milos Jovanovik; Dimitar Trajanov; | arxiv-cs.CL | 2021-02-25 |
| 181 | IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces our systems for all three subtasks of SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning. |
Yuqiang Xie; Luxi Xing; Wei Peng; Yue Hu; | arxiv-cs.CL | 2021-02-25 |
| 182 | DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present several training strategies that, unlike prior approaches, learn to jointly predict words and entities — strategies we compare experimentally on downstream tasks in the TV-Movies domain, such as MovieLens tag prediction from user reviews and natural language movie search. |
YURY ZEMLYANSKIY et. al. | arxiv-cs.CL | 2021-02-25 |
| 183 | Multichannel LSTM-CNN for Telugu Technical Domain Identification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we proposed the Multichannel LSTM-CNN methodology for Technical Domain Identification for Telugu. |
Sunil Gundapu; Radhika Mamidi; | arxiv-cs.CL | 2021-02-24 |
| 184 | OneStop QAMaker: Extract Question-Answer Pairs from Text in A One-Stop Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by such motivation, instead of the conventional pipeline approach, we propose a model named OneStop generate QA pairs from documents in a one-stop approach. |
SHAOBO CUI et. al. | arxiv-cs.CL | 2021-02-24 |
| 185 | Quantum Annealing for Large MIMO Downlink Vector Perturbation Precoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a radically different processing architecture for the downlink VPP problem, one based on Quantum Annealing (QA), to enable the applicability of VPP to large MIMO systems. |
Srikar Kasi; Abhishek Kumar Singh; Davide Venturelli; Kyle Jamieson; | arxiv-cs.NI | 2021-02-24 |
| 186 | Automating Test Case Identification in Open Source Projects on GitHub Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper the following was investigated: (i) the denotation of the test word in different natural languages; (ii) whether the test word correlates with the presence of test cases; and (iii) what testing frameworks are mostly used. |
MATEJ MADEJA et. al. | arxiv-cs.SE | 2021-02-23 |
| 187 | A Relational Tsetlin Machine with Applications to Natural Language Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we increase the computing power of TMs by proposing a first-order logic-based framework with Herbrand semantics. |
Rupsa Saha; Ole-Christoffer Granmo; Vladimir I. Zadorozhny; Morten Goodwin; | arxiv-cs.CL | 2021-02-22 |
| 188 | Learning Compositional Representation for Few-shot Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we propose to extract the attributes from the answers with enough data, which are later composed to constrain the learning of the few-shot ones. We generate the few-shot dataset of VQA with a variety of answers and their attributes without any human effort. |
Dalu Guo; Dacheng Tao; | arxiv-cs.CV | 2021-02-21 |
| 189 | Pruning The Index Contents for Memory Efficient Open-Domain QA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a novel pipeline that demonstrates what is achievable with a combined effort of state-of-the-art approaches. |
Martin Fajcik; Martin Docekal; Karel Ondrej; Pavel Smrz; | arxiv-cs.CL | 2021-02-21 |
| 190 | Multilingual Answer Sentence Reranking Via Automatically Translated Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a study on the design of multilingual Answer Sentence Selection (AS2) models, which are a core component of modern Question Answering (QA) systems. |
Thuy Vu; Alessandro Moschitti; | arxiv-cs.CL | 2021-02-19 |
| 191 | SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a large bilingual dataset, SLAKE, with comprehensive semantic labels annotated by experienced physicians and a new structural medical knowledge base for Med-VQA. |
BO LIU et. al. | arxiv-cs.CV | 2021-02-18 |
| 192 | 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; | arxiv-cs.CV | 2021-02-17 |
| 193 | NoiseQA: Challenge Set Evaluation for User-Centric Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: When Question-Answering (QA) systems are deployed in the real world, users query them through a variety of interfaces, such as speaking to voice assistants, typing questions into … |
ABHILASHA RAVICHANDER et. al. | arxiv-cs.CL | 2021-02-16 |
| 194 | Boosting Low-Resource Biomedical QA Via Entity-Aware Masking Strategies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bootstrap further their domain adaptation, we propose a simple yet unexplored approach, which we call biomedical entity-aware masking (BEM). |
Gabriele Pergola; Elena Kochkina; Lin Gui; Maria Liakata; Yulan He; | arxiv-cs.CL | 2021-02-16 |
| 195 | KnowledgeCheckR: Intelligent Techniques for Counteracting Forgetting IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide an overview of the recommendation approaches integrated in KnowledgeCheckR. |
MARTIN STETTINGER et. al. | arxiv-cs.IR | 2021-02-15 |
| 196 | User-Inspired Posterior Network for Recommendation Reason Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we consider generating the recommendation reason by taking into account not only the product attributes but also the customer-generated product QA discussions. |
HAOLAN ZHAN et. al. | arxiv-cs.IR | 2021-02-15 |
| 197 | From Proper Scoring Rules to Max-Min Optimal Forecast Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We justify this correspondence in several ways: – QA pooling with respect to the two most well-studied scoring rules (quadratic and logarithmic) corresponds to the two most well-studied forecast aggregation methods (linear and logarithmic). |
Eric Neyman; Tim Roughgarden; | arxiv-cs.GT | 2021-02-14 |
| 198 | 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; Pat Verga; Bhuwan Dhingra; Ruslan Salakhutdinov; William W. Cohen; | arxiv-cs.AI | 2021-02-13 |
| 199 | PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To facilitate improved QA-pair models, we introduce Probably Asked Questions (PAQ), a very large resource of 65M automatically-generated QA-pairs. |
PATRICK LEWIS et. al. | arxiv-cs.CL | 2021-02-13 |
| 200 | Optimizing Inference Performance of Transformers on CPUs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Focusing on the highly popular BERT model, we identify key components of the Transformer architecture where the bulk of the computation happens, and propose three optimizations to speed them up. |
Dave Dice; Alex Kogan; | arxiv-cs.CL | 2021-02-12 |
| 201 | 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. | arxiv-cs.CV | 2021-02-11 |
| 202 | Biomedical Question Answering: A Comprehensive Review Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we provide a critical review of recent efforts in BQA. |
QIAO JIN et. al. | arxiv-cs.CL | 2021-02-10 |
| 203 | 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; | arxiv-cs.IR | 2021-02-10 |
| 204 | Decontextualization: Making Sentences Stand-Alone Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present preliminary studies that show the value of sentence decontextualization in a user facing task, and as preprocessing for systems that perform document understanding. We describe an annotation procedure, collect data on the Wikipedia corpus, and use the data to train models to automatically decontextualize sentences. |
EUNSOL CHOI et. al. | arxiv-cs.CL | 2021-02-09 |
| 205 | Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose graph-based methods to retrieve them. |
Nan Shao; Yiming Cui; Ting Liu; Shijin Wang; Guoping Hu; | arxiv-cs.CL | 2021-02-07 |
| 206 | Think You Have Solved Direct-Answer Question Answering? Try ARC-DA, The Direct-Answer AI2 Reasoning Challenge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe the conversion approach taken, appropriate evaluation metrics, and several strong models. We present the ARC-DA dataset, a direct-answer (open response, freeform) version of the ARC (AI2 Reasoning Challenge) multiple-choice dataset. |
SUMITHRA BHAKTHAVATSALAM et. al. | arxiv-cs.CL | 2021-02-05 |
| 207 | Model Agnostic Answer Reranking System for Adversarial Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a simple model-agnostic approach to this problem that can be applied directly to any QA model without any retraining. |
Sagnik Majumder; Chinmoy Samant; Greg Durrett; | arxiv-cs.CL | 2021-02-05 |
| 208 | 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; | arxiv-cs.CL | 2021-02-04 |
| 209 | ChainCQG: Flow-Aware Conversational Question Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a number of novel strategies to improve conversational flow and accommodate varying question types and overall fluidity. |
Jing Gu; Mostafa Mirshekari; Zhou Yu; Aaron Sisto; | arxiv-cs.AI | 2021-02-04 |
| 210 | Answer Questions with Right Image Regions: A Visual Attention Regularization Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, in this paper, we devise a novel visual attention regularization approach, namely AttReg, for better visual grounding in VQA. |
YIBING LIU et. al. | arxiv-cs.CV | 2021-02-03 |
| 211 | QuizCram: A Quiz-Driven Lecture Viewing Interface Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our user study comparing QuizCram to in-video quizzes found that users practice answering and reviewing questions more when using QuizCram, and are better able to remember answers to questions they encountered. |
Geza Kovacs; Darren Edge; | arxiv-cs.HC | 2021-02-02 |
| 212 | Commonsense Knowledge Mining from Term Definitions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate a few machine learning approaches to mining commonsense knowledge triples using dictionary term definitions as inputs and provide some initial evaluation of the results. |
Zhicheng Liang; Deborah L. McGuinness; | arxiv-cs.CL | 2021-02-01 |
| 213 | Hierarchical Ranking for Answer Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel strategy for answer selection, called hierarchical ranking. |
Hang Gao; Mengting Hu; Renhong Cheng; Tiegang Gao; | arxiv-cs.CL | 2021-02-01 |
| 214 | Can Small and Synthetic Benchmarks Drive Modeling Innovation? A Retrospective Study of Question Answering Modeling Approaches Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Datasets are not only resources for training accurate, deployable systems, but are also benchmarks for developing new modeling approaches. We carefully construct small, targeted synthetic benchmarks that do not resemble natural language, yet have high concurrence with SQuAD, demonstrating that naturalness and size are not necessary for reflecting historical modeling improvements on SQuAD. |
Nelson F. Liu; Tony Lee; Robin Jia; Percy Liang; | arxiv-cs.CL | 2021-02-01 |
| 215 | Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate this question. We collect a large-scale multi-subject multiple-choice question-answering dataset, ExamQA, and use incomplete and noisy snippets returned by a web search engine as the relevant context for each question-answering instance to convert it into a weakly-labeled MRC instance. |
Dian Yu; Kai Sun; Dong Yu; Claire Cardie; | arxiv-cs.CL | 2021-02-01 |
| 216 | Revamp: Enhancing Accessible Information Seeking Experience of Online Shopping for Blind Or Low Vision Users Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address those challenges, we propose Revamp, a system that leverages customer reviews for interactive information retrieval. |
RUOLIN WANG et. al. | arxiv-cs.HC | 2021-01-31 |
| 217 | An Empirical Study on The Generalization Power of Neural Representations Learned Via Visual Guessing Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two ways to exploit playing guessing games: 1) a supervised learning scenario in which the agent learns to mimic successful guessing games and 2) a novel way for an agent to play by itself, called Self-play via Iterated Experience Learning (SPIEL). |
ALESSANDRO SUGLIA et. al. | arxiv-cs.CL | 2021-01-31 |
| 218 | 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 \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. |
XUDONG LIN et. al. | arxiv-cs.CV | 2021-01-28 |
| 219 | Modeling Context in Answer Sentence Selection Systems on A Latency Budget Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present an approach to efficiently incorporate contextual information in AS2 models. |
Rujun Han; Luca Soldaini; Alessandro Moschitti; | arxiv-cs.CL | 2021-01-28 |
| 220 | VisualMRC: Machine Reading Comprehension on Document Images IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we introduce a new visual machine reading comprehension dataset, named VisualMRC, wherein given a question and a document image, a machine reads and comprehends texts in the image to answer the question in natural language. |
Ryota Tanaka; Kyosuke Nishida; Sen Yoshida; | arxiv-cs.CL | 2021-01-27 |
| 221 | Powering COVID-19 Community Q&A with Curated Side Information IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate the effectiveness of different attention based neural models that can directly exploit side information available in technical documents or verified forums (e.g., research publications on COVID-19 or WHO website). |
Manisha Verma; Kapil Thadani; Shaunak Mishra; | arxiv-cs.IR | 2021-01-27 |
| 222 | Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence we propose Weakly-Supervised Neuro-Symbolic Module Network (WNSMN) trained with answers as the sole supervision for numerical reasoning based MRC. |
Amrita Saha; Shafiq Joty; Steven C. H. Hoi; | arxiv-cs.CL | 2021-01-27 |
| 223 | Knowledge-driven Natural Language Understanding of English Text and Its Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Keeping this in mind, we have introduced a novel knowledge driven semantic representation approach for English text. |
Kinjal Basu; Sarat Varanasi; Farhad Shakerin; Joaquin Arias; Gopal Gupta; | arxiv-cs.CL | 2021-01-27 |
| 224 | LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new dataset by converting the QA-SRL 2.0 dataset to a large-scale OIE dataset (LSOIE). |
Jacob Solawetz; Stefan Larson; | arxiv-cs.CL | 2021-01-26 |
| 225 | Representations for Question Answering from Documents with Tables and Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we aim to improve question answering from tables by refining table representations based on information from surrounding text. |
Vicky Zayats; Kristina Toutanova; Mari Ostendorf; | arxiv-cs.CL | 2021-01-26 |
| 226 | Meta-Learning for Effective Multi-task and Multilingual Modelling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a meta-learning approach to learn the interactions between both tasks and languages. |
Ishan Tarunesh; Sushil Khyalia; Vishwajeet Kumar; Ganesh Ramakrishnan; Preethi Jyothi; | arxiv-cs.CL | 2021-01-25 |
| 227 | A2P-MANN: Adaptive Attention Inference Hops Pruned Memory-Augmented Neural Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, to limit the number of required attention inference hops in memory-augmented neural networks, we propose an online adaptive approach called A2P-MANN. |
Mohsen Ahmadzadeh; Mehdi Kamal; Ali Afzali-Kusha; Massoud Pedram; | arxiv-cs.CL | 2021-01-24 |
| 228 | Towards Natural Language Question Answering Over Earth Observation Linked Data Using Attention-based Neural Machine Translation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper seeks to study and analyze the use of RNN-based neural machine translation with attention for transforming natural language questions into GeoSPARQL queries. |
Abhishek V. Potnis; Rajat C. Shinde; Surya S. Durbha; | arxiv-cs.CL | 2021-01-23 |
| 229 | Visual Question Answering Based on Local-Scene-Aware Referring Expression Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, we propose the use of text expressions generated for images, because such expressions have few structural constraints and can provide richer descriptions of images. |
Jung-Jun Kim; Dong-Gyu Lee; Jialin Wu; Hong-Gyu Jung; Seong-Whan Lee; | arxiv-cs.CV | 2021-01-22 |
| 230 | Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper improves the learning of dense text retrieval using ANCE, which selects global negatives with bigger gradient norms using an asynchronously updated ANN index. |
LEE XIONG et. al. | iclr | 2021-01-21 |
| 231 | Open Question Answering Over Tables and Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the new task of answering open-domain questions answering over web tables and text and design new techniques: 1) fused retrieval 2) cross-block reader to resolve the challenges posed in the new task. |
Wenhu Chen; Ming-Wei Chang; Eva Schlinger; William Yang Wang; William W. Cohen; | iclr | 2021-01-21 |
| 232 | Learning to Deceive Knowledge Graph Augmented Models Via Targeted Perturbation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our findings raise doubts about KG-augmented models’ ability to leverage KG information and provide plausible explanations. |
MRIGANK RAMAN et. al. | iclr | 2021-01-21 |
| 233 | Distilling Knowledge from Reader to Retriever for Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a technique to learn retriever models for downstream tasks, inspired by knowledge distillation, and which does not require annotated pairs of query and documents. |
Gautier Izacard; Edouard Grave; | iclr | 2021-01-21 |
| 234 | Fast Clustering of Short Text Streams Using Efficient Cluster Indexing and Dynamic Similarity Thresholds IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this challenge, we propose a fast short text stream clustering method (called FastStream) that efficiently index the clusters using inverted index and compute similarity between a text and a selected number of clusters while assigning a text to a cluster. |
Md Rashadul Hasan Rakib; Muhammad Asaduzzaman; | arxiv-cs.IR | 2021-01-21 |
| 235 | Learning Reasoning Paths Over Semantic Graphs for Video-grounded Dialogues Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel approach to learn reasoning paths over semantic graphs which are built upon dialogue context at each turn, for video-grounded dialogues. |
Hung Le; Nancy F. Chen; Steven Hoi; | iclr | 2021-01-21 |
| 236 | Zero-shot Generalization in Dialog State Tracking Through Generative Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel ontology-free framework that supports natural language queries for unseen constraints and slots in multi-domain task-oriented dialogs. |
SHUYANG LI et. al. | arxiv-cs.CL | 2021-01-20 |
| 237 | Towards Confident Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel post-prediction confidence estimation model, which we call Mr.C (short for Mr. Confident), that can be trained to improve a system’s ability to refrain from making incorrect predictions with improvements of up to 4 points as measured by Area Under the Curve (AUC) scores. |
Rishav Chakravarti; Avirup Sil; | arxiv-cs.CL | 2021-01-19 |
| 238 | Tip of The Tongue Known-Item Retrieval: A Case Study in Movie Identification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using movie search as a case study, we explore the characteristics of questions posed by searchers in TOT states in a community question answering website. |
JAIME ARGUELLO et. al. | arxiv-cs.IR | 2021-01-18 |
| 239 | Mitigating The Position Bias of Transformer Models in Passage Re-Ranking IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a debiasing method for retrieval datasets. |
Sebastian Hofstätter; Aldo Lipani; Sophia Althammer; Markus Zlabinger; Allan Hanbury; | arxiv-cs.IR | 2021-01-18 |
| 240 | Incremental Knowledge Based Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new incremental KBQA learning framework that can progressively expand learning capacity as humans do. |
Yongqi Li; Wenjie Li; Liqiang Nie; | arxiv-cs.CL | 2021-01-18 |
| 241 | HySTER: A Hybrid Spatio-Temporal Event Reasoner IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the HySTER: a Hybrid Spatio-Temporal Event Reasoner to reason over physical events in videos. |
Theophile Sautory; Nuri Cingillioglu; Alessandra Russo; | arxiv-cs.CV | 2021-01-17 |
| 242 | What Makes Good In-Context Examples for GPT-$3$? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate whether there are more effective strategies for judiciously selecting in-context examples (relative to random sampling) that better leverage GPT-$3$’s few-shot capabilities. |
JIACHANG LIU et. al. | arxiv-cs.CL | 2021-01-17 |
| 243 | Match-Ignition: Plugging PageRank Into Transformer for Long-form Text Matching IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the effectiveness and efficiency problem, we propose a novel hierarchical noise filtering model in this paper, namely Match-Ignition. |
Liang Pang; Yanyan Lan; Xueqi Cheng; | arxiv-cs.CL | 2021-01-16 |
| 244 | Understanding in Artificial Intelligence IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show how progress has been made in benchmark development to measure understanding capabilities of AI methods and we review as well how current methods develop understanding capabilities. |
STEFAN MAETSCHKE et. al. | arxiv-cs.AI | 2021-01-16 |
| 245 | Latent Variable Models for Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose latent variable models for VQA where extra information (e.g. captions and answer categories) are incorporated as latent variables to improve inference, which in turn benefits question-answering performance. |
Zixu Wang; Yishu Miao; Lucia Specia; | arxiv-cs.CV | 2021-01-16 |
| 246 | 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; | arxiv-cs.CL | 2021-01-16 |
| 247 | Coarse-grained Decomposition and Fine-grained Interaction for Multi-hop Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a new model architecture for multi-hop question answering, by applying two completion strategies: (1) Coarse-Grain complex question Decomposition (CGDe) strategy are introduced to decompose complex question into simple ones under the condition of without any additional annotations (2) Fine-Grained Interaction (FGIn) strategy are introduced to better represent each word in the document and extract more comprehensive and accurate sentences related to the inference path. |
Xing Cao; Yun Liu; | arxiv-cs.CL | 2021-01-15 |
| 248 | Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The purpose of this project is to evaluate three language models named BERT, ALBERT, and LongFormer on the Question Answering dataset called DuoRC. |
Alex John Quijano; Sam Nguyen; Juanita Ordonez; | arxiv-cs.CL | 2021-01-15 |
| 249 | Reasoning Over Vision and Language: Exploring The Benefits of Supplemental Knowledge IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We use an auxiliary training objective that encourages the learned representations to align with graph embeddings of matching entities in a KB. |
Violetta Shevchenko; Damien Teney; Anthony Dick; Anton van den Hengel; | arxiv-cs.CV | 2021-01-15 |
| 250 | Recent Advances in Video Question Answering: A Review of Datasets and Methods IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this survey, we review a number of methods and datasets for the task of VQA. |
Devshree Patel; Ratnam Parikh; Yesha Shastri; | arxiv-cs.CV | 2021-01-14 |
| 251 | Understanding The Role of Scene Graphs in Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore the use of scene graphs for solving the VQA task. |
VINAY DAMODARAN et. al. | arxiv-cs.CV | 2021-01-14 |
| 252 | Neural Sequence-to-grid Module for Learning Symbolic Rules IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve this difficulty, we propose a neural sequence-to-grid (seq2grid) module, an input preprocessor that automatically segments and aligns an input sequence into a grid. |
Segwang Kim; Hyoungwook Nam; Joonyoung Kim; Kyomin Jung; | arxiv-cs.LG | 2021-01-13 |
| 253 | Predicting Relative Depth Between Objects from Semantic Features IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper the extent to which semantic features can predict course relative depth is investigated. |
Stefan Cassar; Adrian Muscat; Dylan Seychell; | arxiv-cs.CV | 2021-01-12 |
| 254 | Latent Alignment of Procedural Concepts in Multimodal Recipes IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. |
Hossein Rajaby Faghihi; Roshanak Mirzaee; Sudarshan Paliwal; Parisa Kordjamshidi; | arxiv-cs.CL | 2021-01-12 |
| 255 | A Neural Question Answering System for Basic Questions About Subroutines IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take initial steps to bringing state-of-the-art neural QA technologies to Software Engineering applications by designing a context-based QA system for basic questions about subroutines. |
Aakash Bansal; Zachary Eberhart; Lingfei Wu; Collin McMillan; | arxiv-cs.SE | 2021-01-11 |
| 256 | Improving Multi-hop Knowledge Base Question Answering By Learning Intermediate Supervision Signals IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. |
Gaole He; Yunshi Lan; Jing Jiang; Wayne Xin Zhao; Ji-Rong Wen; | arxiv-cs.CL | 2021-01-11 |
| 257 | Explain and Predict, and Then Predict Again IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel yet simple approach ExPred, that uses multi-task learning in the explanation generation phase effectively trading-off explanation and prediction losses. |
Zijian Zhang; Koustav Rudra; Avishek Anand; | arxiv-cs.CL | 2021-01-11 |
| 258 | Learning Better Sentence Representation with Syntax Information IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach to combining syntax information with a pre-trained language model. |
Chen Yang; | arxiv-cs.CL | 2021-01-09 |
| 259 | A Novel Word Sense Disambiguation Approach Using WordNet Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel knowledge-based word sense disambiguation algorithm, namely Sequential Contextual Similarity Matrix Multiplication (SCSMM). |
Mohannad AlMousa; Rachid Benlamri; Richard Khoury; | arxiv-cs.CL | 2021-01-08 |
| 260 | EfficientQA : A RoBERTa Based Phrase-Indexed Question-Answering System IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the possibility to transfer the natural language understanding of language models into dense vectors representing questions and answer candidates, in order to make the task of question-answering compatible with a simple nearest neighbor search task. |
Sofian Chaybouti; Achraf Saghe; Aymen Shabou; | arxiv-cs.CL | 2021-01-06 |
| 261 | SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce SF-QA: simple and fair evaluation framework for open-domain QA. |
Xiaopeng Lu; Kyusong Lee; Tiancheng Zhao; | arxiv-cs.CL | 2021-01-06 |
| 262 | Did Aristotle Use A Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce StrategyQA, a question answering (QA) benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. |
MOR GEVA et. al. | arxiv-cs.CL | 2021-01-06 |
| 263 | Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss a framework for calculating similarities between a given input query and a set of predefined questions to retrieve the question which matches to it the most. |
Ankush Chopra; Shruti Agrawal; Sohom Ghosh; | arxiv-cs.CL | 2021-01-06 |
| 264 | Personalized Food Recommendation As Constrained Question Answering Over A Large-scale Food Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we propose a novel problem formulation for food recommendation, modeling this task as constrained question answering over a large-scale food knowledge base/graph (KBQA). To validate this idea, we create a QA style dataset for personalized food recommendation based on a large-scale food knowledge graph and health guidelines. |
Yu Chen; Ananya Subburathinam; Ching-Hua Chen; Mohammed J. Zaki; | arxiv-cs.CL | 2021-01-05 |
| 265 | End-to-End Video Question-Answer Generation with Generator-Pretester Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel model Generator-Pretester Network that focuses on two components: (1) The Joint Question-Answer Generator (JQAG) which generates a question with its corresponding answer to allow Video Question Answering training. |
HUNG-TING SU et. al. | arxiv-cs.MM | 2021-01-05 |
| 266 | Modeling Global Semantics for Question Answering Over Knowledge Bases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a relational graph convolutional network (RGCN)-based model gRGCN for semantic parsing in KBQA. |
Peiyun Wu; Yunjie Wu; Linjuan Wu; Xiaowang Zhang; Zhiyong Feng; | arxiv-cs.AI | 2021-01-05 |
| 267 | Coreference Resolution In Research Papers From Multiple Domains IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the task of coreference resolution in research papers and subsequent knowledge graph population. We present the following contributions: (1) We annotate a corpus for coreference resolution that comprises 10 different scientific disciplines from Science, Technology, and Medicine (STM); (2) We propose transfer learning for automatic coreference resolution in research papers; (3) We analyse the impact of coreference resolution on knowledge graph (KG) population; (4) We release a research KG that is automatically populated from 55,485 papers in 10 STM domains. |
Arthur Brack; Daniel Uwe Müller; Anett Hoppe; Ralph Ewerth; | arxiv-cs.IR | 2021-01-04 |
| 268 | Transformers in Vision: A Survey IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. |
SALMAN KHAN et. al. | arxiv-cs.CV | 2021-01-04 |
| 269 | Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we review the latest research trends in OpenQA, with particular attention to systems that incorporate neural MRC techniques. |
FENGBIN ZHU et. al. | arxiv-cs.AI | 2021-01-03 |
| 270 | Benchmarking Knowledge-Enhanced Commonsense Question Answering Via Knowledge-to-Text Transformation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. |
Ning Bian; Xianpei Han; Bo Chen; Le Sun; | arxiv-cs.CL | 2021-01-03 |
| 271 | Which Linguist Invented The Lightbulb? Presupposition Verification For Question-Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We report our progress in tackling each subproblem, and present a preliminary approach to integrating these steps into an existing QA system. |
Najoung Kim; Ellie Pavlick; Burcu Karagol Ayan; Deepak Ramachandran; | arxiv-cs.CL | 2021-01-02 |
| 272 | Baleen: Robust Multi-Hop Reasoning at Scale Via Condensed Retrieval IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tame the search space, we propose condensed retrieval, a pipeline that summarizes the retrieved passages after each hop into a single compact context. |
Omar Khattab; Christopher Potts; Matei Zaharia; | arxiv-cs.CL | 2021-01-02 |
| 273 | Few-Shot Question Answering By Pretraining Span Selection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose a new pretraining scheme that is more suitable for extractive question answering. |
Ori Ram; Yuval Kirstain; Jonathan Berant; Amir Globerson; Omer Levy; | arxiv-cs.CL | 2021-01-02 |
| 274 | End-to-End Training Of Neural Retrievers For Open-Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we systematically study retriever pre-training. |
DEVENDRA SINGH SACHAN et. al. | arxiv-cs.CL | 2021-01-02 |
| 275 | RiddleSense: Answering Riddle Questions As Commonsense Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose RiddleSense, a novel multiple-choice question answering challenge for benchmarking higher-order commonsense reasoning models, which is the first large dataset for riddle-style commonsense question answering, where the distractors are crowdsourced from human annotators. |
Bill Yuchen Lin; Ziyi Wu; Yichi Yang; Dong-Ho Lee; Xiang Ren; | arxiv-cs.CL | 2021-01-02 |
| 276 | UnitedQA: A Hybrid Approach For Open Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study a hybrid approach for leveraging the strengths of both models. |
HAO CHENG et. al. | arxiv-cs.CL | 2021-01-01 |
| 277 | Reader-Guided Passage Reranking For Open-Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple and effective passage reranking method, Reader-guIDEd Reranker (Rider), which does not involve any training and reranks the retrieved passages solely based on the top predictions of the reader before reranking. |
YUNING MAO et. al. | arxiv-cs.CL | 2021-01-01 |
| 278 | FiD-Ex: Improving Sequence-to-Sequence Models For Extractive Rationale Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop FiD-Ex, which addresses these shortcomings for seq2seq models by: 1) introducing sentence markers to eliminate explanation fabrication by encouraging extractive generation, 2) using the fusion-in-decoder architecture to handle long input contexts, and 3) intermediate fine-tuning on re-structured open domain QA datasets to improve few-shot performance. |
KUSHAL LAKHOTIA et. al. | arxiv-cs.CL | 2020-12-31 |
| 279 | Seeing Is Knowing! Fact-based Visual Question Answering Using Knowledge Graph Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a novel QA architecture that allows us to reason over incomplete KGs, something current FVQA state-of-the-art (SOTA) approaches lack.We use KG Embeddings, a technique widely used for KG completion, for the downstream task of FVQA. |
Kiran Ramnath; Mark Hasegawa-Johnson; | arxiv-cs.CL | 2020-12-31 |
| 280 | AraGPT2: Pre-Trained Transformer for Arabic Language Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop the first advanced Arabic language generation model, AraGPT2, trained from scratch on a large Arabic corpus of internet text and news articles. |
Wissam Antoun; Fady Baly; Hazem Hajj; | arxiv-cs.CL | 2020-12-31 |
| 281 | Using Natural Language Relations Between Answer Choices For Machine Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method to leverage the natural language relations between the answer choices, such as entailment and contradiction, to improve the performance of machine comprehension. |
Rajkumar Pujari; Dan Goldwasser; | arxiv-cs.CL | 2020-12-31 |
| 282 | Studying Strategically: Learning To Mask For Closed-book QA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to learn the optimal masking strategy for the intermediate pre-training stage. |
QINYUAN YE et. al. | arxiv-cs.CL | 2020-12-31 |
| 283 | ERNIE-DOC: The Retrospective Long-Document Modeling Transformer IF:2 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. | arxiv-cs.CL | 2020-12-31 |
| 284 | HopRetriever: Retrieve Hops Over Wikipedia To Answer Complex Questions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. |
SHAOBO LI et. al. | arxiv-cs.CL | 2020-12-31 |
| 285 | Coreference Reasoning In Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a methodology for creating reading comprehension datasets that better reflect the challenges of coreference reasoning and use it to show that state-of-the-art models still struggle with these phenomena. We will release all the code and the resulting dataset at https://github.com/UKPLab/coref-reasoning-in-qa. |
Mingzhu Wu; Nafise Sadat Moosavi; Dan Roth; Iryna Gurevych; | arxiv-cs.CL | 2020-12-31 |
| 286 | NeurIPS 2020 EfficientQA Competition: Systems, Analyses And Lessons Learned IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this report, we describe the motivation and organization of the competition, review the best submissions, and analyze system predictions to inform a discussion of evaluation for open-domain QA. |
SEWON MIN et. al. | arxiv-cs.CL | 2020-12-31 |
| 287 | Multi-task Retrieval For Knowledge-Intensive Tasks IF:2 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. | arxiv-cs.CL | 2020-12-31 |
| 288 | An Experimental Evaluation Of Transformer-based Language Models In The Biomedical Domain IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Emphasizing the cost of these models, which renders technical replication challenging, this paper summarizes experiments conducted in replicating BioBERT and further pre-training and careful fine-tuning in the biomedical domain. |
PAUL GROUCHY et. al. | arxiv-cs.CL | 2020-12-30 |
| 289 | Presenting A Dataset for Collaborator Recommending Systems in Academic Social Network: A Case Study on ReseachGate IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce two datasets to fill this gap. |
Zahra Roozbahani; Jalal Rezaeenour; Roshan Shahrooei; Hanif Emamgholizadeh; | arxiv-cs.IR | 2020-12-29 |
| 290 | Red Dragon AI At TextGraphs 2020 Shared Task: LIT : LSTM-Interleaved Transformer For Multi-Hop Explanation Ranking IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To counter the limitations of methods that view each query-document pair in isolation, we propose the LSTM-Interleaved Transformer which incorporates cross-document interactions for improved multi-hop ranking. |
Yew Ken Chia; Sam Witteveen; Martin Andrews; | arxiv-cs.CL | 2020-12-28 |
| 291 | BURT: BERT-inspired Universal Representation From Learning Meaningful Segment IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a universal representation model, BURT (BERT-inspired Universal Representation from learning meaningful segmenT), to encode different levels of linguistic unit into the same vector space. |
Yian Li; Hai Zhao; | arxiv-cs.CL | 2020-12-28 |
| 292 | Commonsense Visual Sensemaking For Autonomous Driving: On Generalised Neurosymbolic Online Abduction Integrating Vision And Semantics IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We demonstrate the need and potential of systematically integrated vision and semantics solutions for visual sensemaking in the backdrop of autonomous driving. |
Jakob Suchan; Mehul Bhatt; Srikrishna Varadarajan; | arxiv-cs.AI | 2020-12-28 |
| 293 | Syntax-Enhanced Pre-trained Model IF:2 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. | arxiv-cs.CL | 2020-12-28 |
| 294 | Causal Perception in Question-Answering Systems IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems. |
Po-Ming Law; Leo Yu-Ho Lo; Alex Endert; John Stasko; Huamin Qu; | arxiv-cs.HC | 2020-12-28 |
| 295 | Explaining NLP Models Via Minimal Contrastive Editing (MiCE) IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Minimal Contrastive Editing (MiCE), a method for generating contrastive explanations of model predictions in the form of edits to inputs that change model outputs to the contrast case. |
Alexis Ross; Ana Marasović; Matthew E. Peters; | arxiv-cs.CL | 2020-12-27 |
| 296 | Pivot Through English: Reliably Answering Multilingual Questions Without Document Retrieval IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Within this task setup we propose Reranked Multilingual Maximal Inner Product Search (RM-MIPS), akin to semantic similarity retrieval over the English training set with reranking, which outperforms the strongest baselines by 2.7% on XQuAD and 6.2% on MKQA. |
Ivan Montero; Shayne Longpre; Ni Lao; Andrew J. Frank; Christopher DuBois; | arxiv-cs.CL | 2020-12-27 |
| 297 | Brain-inspired Search Engine Assistant Based On Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a brain-inspired search engine assistant named DeveloperBot based on knowledge graph is proposed, which aligns to the cognitive process of human and has the capacity to answer complex queries with explainability. |
Xuejiao Zhao; Huanhuan Chen; Zhenchang Xing; Chunyan Miao; | arxiv-cs.AI | 2020-12-25 |
| 298 | LOREN: Logic Enhanced Neural Reasoning For Fact Verification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose LOREN, a novel approach for fact verification that integrates both Logic guided Reasoning and Neural inference. |
JIANGJIE CHEN et. al. | arxiv-cs.CL | 2020-12-25 |
| 299 | REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a recursive erasure memory network (REM-Net) to cope with the quality improvement of evidence. |
YINYA HUANG et. al. | arxiv-cs.CL | 2020-12-24 |
| 300 | QUACKIE: A NLP Classification Task With Ground Truth Explanations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a different approach and formulate a specific classification task by diverting question-answering datasets. |
Yves Rychener; Xavier Renard; Djamé Seddah; Pascal Frossard; Marcin Detyniecki; | arxiv-cs.CL | 2020-12-24 |
| 301 | Learning Dense Representations Of Phrases At Scale IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show for the first time that we can learn dense phrase representations alone that achieve much stronger performance in open-domain QA. |
Jinhyuk Lee; Mujeen Sung; Jaewoo Kang; Danqi Chen; | arxiv-cs.CL | 2020-12-23 |
| 302 | Negation In Cognitive Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe an effective procedure to determine the negated event or property in order to replace it with it inverse and our overall system for cognitive reasoning. |
Claudia Schon; Sophie Siebert; Frieder Stolzenburg; | arxiv-cs.CL | 2020-12-23 |
| 303 | A Hierarchical Reasoning Graph Neural Network For The Automatic Scoring Of Answer Transcriptions In Video Job Interviews IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Hierarchical Reasoning Graph Neural Network (HRGNN) for the automatic assessment of question-answer pairs. |
Kai Chen; Meng Niu; Qingcai Chen; | arxiv-cs.CL | 2020-12-22 |
| 304 | Exploring And Analyzing Machine Commonsense Benchmarks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe our initial MCS Benchmark Ontology, an extensible common vocabulary that formalizes benchmark metadata, and showcase how it is supporting the development of a Benchmark tool that enables benchmark exploration and analysis. |
Henrique Santos; Minor Gordon; Zhicheng Liang; Gretchen Forbush; Deborah L. McGuinness; | arxiv-cs.AI | 2020-12-21 |
| 305 | Learning Content And Context With Language Bias For Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel learning strategy named CCB, which forces VQA models to answer questions relying on Content and Context with language Bias. |
CHAO YANG et. al. | arxiv-cs.CV | 2020-12-21 |
| 306 | Object-Centric Diagnosis Of Visual Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The designed model improves the performance on all three metrics over the vanilla neural-symbolic model while inheriting the transparency. |
JIANWEI YANG et. al. | arxiv-cs.CV | 2020-12-21 |
| 307 | On Modality Bias In The TVQA Dataset IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate an inherent bias in the dataset towards the textual subtitle modality. Using this framework we propose subsets of TVQA that respond exclusively to either or both modalities in order to facilitate multimodal modelling as TVQA originally intended. |
Thomas Winterbottom; Sarah Xiao; Alistair McLean; Noura Al Moubayed; | arxiv-cs.CV | 2020-12-18 |
| 308 | Trying Bilinear Pooling In Video-QA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we begin to bridge this research gap by applying BLP techniques to various video-QA benchmarks, namely: TVQA, TGIF-QA, Ego-VQA and MSVD-QA. |
Thomas Winterbottom; Sarah Xiao; Alistair McLean; Noura Al Moubayed; | arxiv-cs.CV | 2020-12-18 |
| 309 | Can Transformers Reason About Effects Of Actions? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A recent work has shown that transformers are able to reason with facts and rules in a limited setting where the rules are natural language expressions of conjunctions of conditions implying a conclusion. We consider four action domains (Blocks World, Logistics, Dock-Worker-Robots and a Generic Domain) in natural language and create QA datasets that involve reasoning about the effects of actions in these domains. |
PRATYAY BANERJEE et. al. | arxiv-cs.CL | 2020-12-17 |
| 310 | MIX : A Multi-task Learning Approach to Solve Open-Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce MIX : a multi-task deep learning approach to solve Open-Domain Question Answering. |
Sofian Chaybouti; Achraf Saghe; Aymen Shabou; | arxiv-cs.CL | 2020-12-17 |
| 311 | Exploring Fluent Query Reformulations With Text-to-Text Transformers And Reinforcement Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explore methods to generate these query reformulations by training reformulators using text-to-text transformers and apply policy-based reinforcement learning algorithms to further encourage reward learning. |
Jerry Zikun Chen; Shi Yu; Haoran Wang; | arxiv-cs.CL | 2020-12-17 |
| 312 | Clinical Temporal Relation Extraction With Probabilistic Soft Logic Regularization And Global Inference IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel method, Clinical Temporal ReLation Exaction with Probabilistic Soft Logic Regularization and Global Inference (CTRL-PG) to tackle the problem at the document level. |
YICHAO ZHOU et. al. | arxiv-cs.CL | 2020-12-16 |
| 313 | Knowledge-Routed Visual Question Reasoning: Challenges For Deep Representation Embedding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. |
Qingxing Cao; Bailin Li; Xiaodan Liang; Keze Wang; Liang Lin; | arxiv-cs.CV | 2020-12-13 |
| 314 | How Question Quality Drives Web Performance In Community Question Answering Sites IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We gathered 15 question-quality related features from one of the largest CQA sites and the site’s pageview data to estimate the scale of the effect in the corresponding time series. |
Alyssa Shuang Sha; Yingnan Shi; Armin Haller; | arxiv-cs.SI | 2020-12-11 |
| 315 | Look Before You Speak: Visually Contextualized Utterances IF:2 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; | arxiv-cs.CV | 2020-12-10 |
| 316 | Bew: Towards Answering Business-Entity-Related Web Questions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a practical approach, called BewQA, that can answer Bew queries by mining a template of the business-related webpages and using the template to guide the search. |
Qingqing Cao; Oriana Riva; Aruna Balasubramanian; Niranjan Balasubramanian; | arxiv-cs.IR | 2020-12-10 |
| 317 | Multilingual Transfer Learning For QA Using Translation As Data Augmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. |
Mihaela Bornea; Lin Pan; Sara Rosenthal; Radu Florian; Avirup Sil; | arxiv-cs.CL | 2020-12-10 |
| 318 | Simple Is Not Easy: A Simple Strong Baseline For TextVQA And TextCaps IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that a simple attention mechanism can do the same or even better job without any bells and whistles. |
Qi Zhu; Chenyu Gao; Peng Wang; Qi Wu; | arxiv-cs.CV | 2020-12-09 |
| 319 | TAP: Text-Aware Pre-training For Text-VQA And Text-Caption IF:2 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. To further improve the performance, we build a large-scale dataset based on the Conceptual Caption dataset, named OCR-CC, which contains 1.4 million scene text-related image-text pairs. |
ZHENGYUAN YANG et. al. | arxiv-cs.CV | 2020-12-08 |
| 320 | CRAFT: A Benchmark For Causal Reasoning About Forces And InTeractions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this ongoing work, we introduce CRAFT, a new visual question answering dataset that requires causal reasoning about physical forces and object interactions. |
TAYFUN ATES et. al. | arxiv-cs.AI | 2020-12-08 |
| 321 | KgPLM: Knowledge-guided Language Model Pre-training Via Generative And Discriminative Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a language model pre-training framework guided by factual knowledge completion and verification, and use the generative and discriminative approaches cooperatively to learn the model. |
Bin He; Xin Jiang; Jinghui Xiao; Qun Liu; | arxiv-cs.CL | 2020-12-07 |
| 322 | Conversational Browsing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To answer these questions, we collected observations of human participants performing a similar task to obtain inspiration for the system design. |
Svitlana Vakulenko; Vadim Savenkov; Maarten de Rijke; | arxiv-cs.IR | 2020-12-07 |
| 323 | FloodNet: A High Resolution Aerial Imagery Dataset For Post Flood Scene Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we compare and contrast the performances of baseline methods for image classification, semantic segmentation, and visual question answering on our dataset. |
MARYAM RAHNEMOONFAR et. al. | arxiv-cs.CV | 2020-12-05 |
| 324 | RPT: Relational Pre-trained Transformer Is Almost All You Need Towards Democratizing Data Preparation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We answer this question by presenting RPT, a denoising auto-encoder for tuple-to-X models (X could be tuple, token, label, JSON, and so on). |
NAN TANG et. al. | arxiv-cs.LG | 2020-12-04 |
| 325 | Question Answering Over Knowledge Bases By Leveraging Semantic Parsing And Neuro-Symbolic Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a semantic parsing and reasoning-based Neuro-Symbolic Question Answering(NSQA) system, that leverages (1) Abstract Meaning Representation (AMR) parses for task-independent question under-standing; (2) a novel path-based approach to transform AMR parses into candidate logical queries that are aligned to the KB; (3) a neuro-symbolic reasoner called Logical Neural Net-work (LNN) that executes logical queries and reasons over KB facts to provide an answer; (4) system of systems approach,which integrates multiple, reusable modules that are trained specifically for their individual tasks (e.g. semantic parsing,entity linking, and relationship linking) and do not require end-to-end training data. |
PAVAN KAPANIPATHI et. al. | arxiv-cs.CL | 2020-12-03 |
| 326 | End-to-End QA On COVID-19: Domain Adaptation With Synthetic Training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore the application of synthetically generated QA examples to improve performance on closed-domain retrieval and MRC. |
REVANTH GANGI REDDY et. al. | arxiv-cs.CL | 2020-12-02 |
| 327 | SeMantic AnsweR Type Prediction Task (SMART) At ISWC 2020 Semantic Web Challenge IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Each year the International Semantic Web Conference accepts a set of Semantic Web Challenges to establish competitions that will advance the state of the art solutions in any … |
NANDANA MIHINDUKULASOORIYA et. al. | arxiv-cs.AI | 2020-12-01 |
| 328 | Just Ask: Learning to Answer Questions from Millions of Narrated Videos IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to avoid manual annotation and generate a large-scale training dataset for video question answering making use of automatic cross-modal supervision. Given narrated videos, we then automatically generate the HowToVQA69M dataset with 69M video-question-answer triplets. Finally, for a detailed evaluation we introduce a new VideoQA dataset with reduced language biases and high-quality redundant manual annotations. |
Antoine Yang; Antoine Miech; Josef Sivic; Ivan Laptev; Cordelia Schmid; | arxiv-cs.CV | 2020-12-01 |
| 329 | ClimaText: A Dataset For Climate Change Topic Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce \textsc{ClimaText}, a dataset for sentence-based climate change topic detection, which we make publicly available. |
Francesco S. Varini; Jordan Boyd-Graber; Massimiliano Ciaramita; Markus Leippold; | arxiv-cs.CL | 2020-12-01 |
| 330 | Open-Ended Multi-Modal Relational Reason For Video Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we are going to discuss the related questions about this kind of interaction, the techniques we used in this work, and how we conduct our research. |
Haozheng Luo; Ruiyang Qin; | arxiv-cs.AI | 2020-12-01 |
| 331 | Meta-Embeddings For Natural Language Inference And Semantic Similarity Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to use Meta Embedding derived from few State-of-the-Art (SOTA) models to efficiently tackle mainstream NLP tasks like classification, semantic relatedness, and text similarity. |
Shree Charran R; Rahul Kumar Dubey; | arxiv-cs.CL | 2020-12-01 |
| 332 | How Can We Know When Language Models Know? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we ask the question how can we know when language models know, with confidence, the answer to a particular query? |
Zhengbao Jiang; Jun Araki; Haibo Ding; Graham Neubig; | arxiv-cs.CL | 2020-12-01 |
| 333 | A Data-Driven Study of Commonsense Knowledge Using The ConceptNet Knowledge Base IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose and conduct a systematic study to enable a deeper understanding of commonsense knowledge by doing an empirical and structural analysis of the ConceptNet knowledge base. |
Ke Shen; Mayank Kejriwal; | arxiv-cs.AI | 2020-11-28 |
| 334 | Point And Ask: Incorporating Pointing Into Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we further expand this space by considering visual questions that include a spatial point of reference. Concretely, we (1) introduce and motivate point-input questions as an extension of VQA, (2) define three novel classes of questions within this space, and (3) for each class, introduce both a benchmark dataset and a series of baseline models to handle its unique challenges. |
Arjun Mani; Will Hinthorn; Nobline Yoo; Olga Russakovsky; | arxiv-cs.CV | 2020-11-27 |
| 335 | FFCI: A Framework For Interpretable Automatic Evaluation Of Summarization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose FFCI, a framework for automatic summarization evaluation that comprises four elements: Faithfulness, Focus, Coverage, and Inter-sentential coherence. |
Fajri Koto; Jey Han Lau; Timothy Baldwin; | arxiv-cs.CL | 2020-11-27 |
| 336 | Braid: Weaving Symbolic And Neural Knowledge Into Coherent Logical Explanations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe the reasoning algorithms used in Braid-BC (the backchaining component of Braid), and their implementation in a distributed task-based framework that builds proof/explanation graphs for an input query in a scalable manner. |
Aditya Kalyanpur; Tom Breloff; David Ferrucci; Adam Lally; John Jantos; | arxiv-cs.CL | 2020-11-26 |
| 337 | Learning From Lexical Perturbations For Consistent Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach to address this issue based on modular networks, which creates two questions related by linguistic perturbations and regularizes the visual reasoning process between them to be consistent during training. |
SPENCER WHITEHEAD et. al. | arxiv-cs.CV | 2020-11-26 |
| 338 | Answering Ambiguous Questions Through Generative Evidence Fusion And Round-Trip Prediction IF:2 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 generate question-answer pairs. |
YIFAN GAO et. al. | arxiv-cs.CL | 2020-11-26 |
| 339 | A Question-answering System For Aircraft Pilots’ Documentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: After describing each module of the dialog system, we present a multi-task based approach for the QA module which enables performance improvement on a Flight Crew Operating Manual (FCOM) dataset. |
Alexandre Arnold; Gérard Dupont; Félix Furger; Catherine Kobus; François Lancelot; | arxiv-cs.CL | 2020-11-26 |
| 340 | A Panoramic Survey Of Natural Language Processing In The Arab World IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: NLP researchers pride themselves on developing language independent models and tools that can be applied to all human languages, e.g. machine translation systems can be built for a variety of languages using the same basic mechanisms and models. |
KAREEM DARWISH et. al. | arxiv-cs.CL | 2020-11-25 |
| 341 | XTQA: Span-Level Explanations Of The Textbook Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We argue that the explainability of this task should place students as a key aspect to be considered. |
JIE MA et. al. | arxiv-cs.CL | 2020-11-25 |
| 342 | Zero-Shot Visual Slot Filling As Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new approach to visual zero-shot slot filling. |
Larry Heck; Simon Heck; | arxiv-cs.AI | 2020-11-24 |
| 343 | Domain-Transferable Method For Named Entity Recognition Task IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes a method to learn a domain-specific NER model for an arbitrary set of named entities when domain-specific supervision is not available. |
Vladislav Mikhailov; Tatiana Shavrina; | arxiv-cs.CL | 2020-11-24 |
| 344 | Dual Supervision Framework For Relation Extraction With Distant Supervision And Human Annotation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To take advantage of the high accuracy of human annotation and the cheap cost of distant supervision, we propose the dual supervision framework which effectively utilizes both types of data. |
Woohwan Jung; Kyuseok Shim; | arxiv-cs.CL | 2020-11-23 |
| 345 | Large Scale Multimodal Classification Using An Ensemble Of Transformer Models And Co-Attention IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we describe our methodology and results for the SIGIR eCom Rakuten Data Challenge. |
Varnith Chordia; Vijay Kumar BG; | arxiv-cs.AI | 2020-11-23 |
| 346 | Siamese Tracking With Lingual Object Constraints IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper explores, tracking visual objects subjected to additional lingual constraints. |
Maximilian Filtenborg; Efstratios Gavves; Deepak Gupta; | arxiv-cs.CV | 2020-11-23 |
| 347 | Cross-Domain Generalization Through Memorization: A Study Of Nearest Neighbors In Neural Duplicate Question Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage neural representations and study nearest neighbors for cross-domain generalization in DQD. |
Yadollah Yaghoobzadeh; Alexandre Rochette; Timothy J. Hazen; | arxiv-cs.CL | 2020-11-22 |
| 348 | LRTA: A Transparent Neural-Symbolic Reasoning Framework With Modular Supervision For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose LRTA [Look, Read, Think, Answer], a transparent neural-symbolic reasoning framework for visual question answering that solves the problem step-by-step like humans and provides human-readable form of justification at each step. |
Weixin Liang; Feiyang Niu; Aishwarya Reganti; Govind Thattai; Gokhan Tur; | arxiv-cs.CL | 2020-11-21 |
| 349 | Self-Supervised Learning With Cross-modal Transformers For Emotion Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extend self-supervised training to multi-modal applications. |
Aparna Khare; Srinivas Parthasarathy; Shiva Sundaram; | arxiv-cs.CL | 2020-11-20 |
| 350 | What Do We Expect From Multiple-choice QA Systems? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we consider a top performing model on several Multiple Choice Question Answering (MCQA) datasets, and evaluate it against a set of expectations one might have from such a model, using a series of zero-information perturbations of the model’s inputs. |
Krunal Shah; Nitish Gupta; Dan Roth; | arxiv-cs.CL | 2020-11-20 |
| 351 | Logically Consistent Loss For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new model-agnostic logic constraint to tackle this issue by formulating a logically consistent loss in the multi-task learning framework as well as a data organisation called family-batch and hybrid-batch. |
Anh-Cat Le-Ngo; Truyen Tran; Santu Rana; Sunil Gupta; Svetha Venkatesh; | arxiv-cs.CV | 2020-11-19 |
| 352 | Diverse And Non-redundant Answer Set Extraction On Community QA Based On DPPs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new task of selecting a diverse and non-redundant answer set rather than ranking the answers. We built a dataset focusing on a Japanese CQA site, and the experiments on this dataset demonstrated that the proposed method outperformed several baseline methods. |
Shogo Fujita; Tomohide Shibata; Manabu Okumura; | arxiv-cs.CL | 2020-11-18 |
| 353 | Do Fine-tuned Commonsense Language Models Really Generalize? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the generalization issue in detail by designing and conducting a rigorous scientific study. |
Mayank Kejriwal; Ke Shen; | arxiv-cs.CL | 2020-11-18 |
| 354 | EasyTransfer — A Simple And Scalable Deep Transfer Learning Platform For NLP Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The literature has witnessed the success of applying deep Transfer Learning (TL) algorithms to many NLP applications, yet it is not easy to build a simple and scalable TL toolkit for this purpose. |
MINGHUI QIU et. al. | arxiv-cs.CL | 2020-11-18 |
| 355 | Language Models Are Few-Shot Learners IF:7 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. |
TOM BROWN et. al. | nips | 2020-11-17 |
| 356 | Large-Scale Adversarial Training For Vision-and-Language Representation Learning IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. |
ZHE GAN et. al. | nips | 2020-11-17 |
| 357 | Retrieval-Augmented Generation For Knowledge-Intensive NLP Tasks IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. |
PATRICK LEWIS et. al. | nips | 2020-11-17 |
| 358 | Big Bird: Transformers For Longer Sequences IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. |
MANZIL ZAHEER et. al. | nips | 2020-11-17 |
| 359 | H-Mem: Harnessing Synaptic Plasticity With Hebbian Memory Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose Hebbian Memory Networks (H-Mems), a simple neural network model that is built around a core hetero-associative network subject to Hebbian plasticity. |
Thomas Limbacher; Robert Legenstein; | nips | 2020-11-17 |
| 360 | Pushing The Limits Of Narrow Precision Inferencing At Cloud Scale With Microsoft Floating Point IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the limits of Microsoft Floating Point (MSFP), a new class of datatypes developed for production cloud-scale inferencing on custom hardware. |
BITA DARVISH ROUHANI et. al. | nips | 2020-11-17 |
| 361 | Faithful Embeddings For Knowledge Base Queries IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this problem with a novel QE method that is more faithful to deductive reasoning, and show that this leads to better performance on complex queries to incomplete KBs. |
Haitian Sun; Andrew Arnold; Tania Bedrax Weiss; Fernando Pereira; William W. Cohen; | nips | 2020-11-17 |
| 362 | Bayesian Attention Modules IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a scalable stochastic version of attention that is easy to implement and optimize. |
Xinjie Fan; Shujian Zhang; Bo Chen; Mingyuan Zhou; | nips | 2020-11-17 |
| 363 | Hierarchical Poset Decoding For Compositional Generalization In Language IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel hierarchical poset decoding paradigm for compositional generalization in language. |
Yinuo Guo; Zeqi Lin; Jian-Guang Lou; Dongmei Zhang; | nips | 2020-11-17 |
| 364 | Sparse And Continuous Attention Mechanisms IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper expands that work in two directions: first, we extend alpha-entmax to continuous domains, revealing a link with Tsallis statistics and deformed exponential families. Second, we introduce continuous-domain attention mechanisms, deriving efficient gradient backpropagation algorithms for alpha in {1,2}. |
ANDR� MARTINS et. al. | nips | 2020-11-17 |
| 365 | Efficient Distance Approximation For Structured High-Dimensional Distributions Via Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we present algorithms for the following problems (where dTV is the total variation distance): Given sample access to two Bayesian networks P1 and P2 over known directed acyclic graphs G1 and G2 having n nodes and bounded in-degree, approximate dTV(P1, P2) to within additive error ? using poly(n, 1/?) samples and time. |
Arnab Bhattacharyya; Sutanu Gayen; Kuldeep S Meel; N. V. Vinodchandran; | nips | 2020-11-17 |
| 366 | Removing Bias In Multi-modal Classifiers: Regularization By Maximizing Functional Entropies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this shortcoming, we propose a novel regularization term based on the functional entropy. |
Itai Gat; Idan Schwartz; Alexander Schwing; Tamir Hazan; | nips | 2020-11-17 |
| 367 | Multimodal Graph Networks For Compositional Generalization In Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to tackle this challenge by employing neural factor graphs to induce a tighter coupling between concepts in different modalities (e.g. images and text). |
Raeid Saqur; Karthik Narasimhan; | nips | 2020-11-17 |
| 368 | Counterfactual Vision-and-Language Navigation: Unravelling The Unseen Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new learning strategy that learns both from observations and generated counterfactual environments. |
Amin Parvaneh; Ehsan Abbasnejad; Damien Teney; Qinfeng Shi; Anton van den Hengel; | nips | 2020-11-17 |
| 369 | On The Value Of Out-of-Distribution Testing: An Example Of Goodhart's Law Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide short- and long-term solutions to avoid these pitfalls and realize the benefits of OOD evaluation. |
DAMIEN TENEY et. al. | nips | 2020-11-17 |
| 370 | Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases IF:2 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. To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64,331 questions, GrailQA, and provide evaluation settings for all three levels of generalization. |
YU GU et. al. | arxiv-cs.CL | 2020-11-16 |
| 371 | IPerceive: Applying Common-Sense Reasoning To Multi-Modal Dense Video Captioning And Video Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Part of what defines us as human and fundamentally different from machines is our instinct to seek causality behind any association, say an event Y that happened as a direct result of event X. To this end, we propose iPerceive, a framework capable of understanding the why between events in a video by building a common-sense knowledge base using contextual cues to infer causal relationships between objects in the video. |
Aman Chadha; Gurneet Arora; Navpreet Kaloty; | arxiv-cs.CV | 2020-11-16 |
| 372 | NLPGym — A Toolkit For Evaluating RL Agents On Natural Language Processing Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With the work reported here, we therefore release NLPGym, an open-source Python toolkit that provides interactive textual environments for standard NLP tasks such as sequence tagging, multi-label classification, and question answering. |
Rajkumar Ramamurthy; Rafet Sifa; Christian Bauckhage; | arxiv-cs.CL | 2020-11-16 |
| 373 | ActBERT: Learning Global-Local Video-Text Representations IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. |
Linchao Zhu; Yi Yang; | arxiv-cs.CV | 2020-11-14 |
| 374 | Meaningful Answer Generation Of E-Commerce Question-Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the task of product-aware answer generation, which learns to generate an accurate and complete answer from large-scale unlabeled e-commerce reviews and product attributes. |
Shen Gao; Xiuying Chen; Zhaochun Ren; Dongyan Zhao; Rui Yan; | arxiv-cs.CL | 2020-11-14 |
| 375 | Utilizing Bidirectional Encoder Representations From Transformers For Answer Selection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To investigate their effectiveness in such tasks, in this paper, we adopt the pre-trained Bidirectional Encoder Representations from Transformer (BERT) language model and fine-tune it on two Question Answering (QA) datasets and three Community Question Answering (CQA) datasets for the answer selection task. |
Md Tahmid Rahman Laskar; Enamul Hoque; Jimmy Xiangji Huang; | arxiv-cs.CL | 2020-11-13 |
| 376 | Dense Passage Retrieval For Open-Domain Question Answering IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. |
VLADIMIR KARPUKHIN et. al. | emnlp | 2020-11-12 |
| 377 | MAD-X: An Adapter-Based Framework For Multi-Task Cross-Lingual Transfer IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose MAD-X, an adapter-based framework that enables high portability and parameter-efficient transfer to arbitrary tasks and languages by learning modular language and task representations. |
Jonas Pfeiffer; Ivan Vulić; Iryna Gurevych; Sebastian Ruder; | emnlp | 2020-11-12 |
| 378 | Unsupervised Commonsense Question Answering With Self-Talk IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an unsupervised framework based on self-talk as a novel alternative to multiple-choice commonsense tasks. |
Vered Shwartz; Peter West; Ronan Le Bras; Chandra Bhagavatula; Yejin Choi; | emnlp | 2020-11-12 |
| 379 | AmbigQA: Answering Ambiguous Open-domain Questions IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce AmbigQA, a new open-domain question answering task which involves finding every plausible answer, and then rewriting the question for each one to resolve the ambiguity. |
Sewon Min; Julian Michael; Hannaneh Hajishirzi; Luke Zettlemoyer; | emnlp | 2020-11-12 |
| 380 | Unsupervised Question Decomposition For Question Answering IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we propose an algorithm for One-to-N Unsupervised Sequence transduction (ONUS) that learns to map one hard, multi-hop question to many simpler, single-hop sub-questions. |
Ethan Perez; Patrick Lewis; Wen-tau Yih; Kyunghyun Cho; Douwe Kiela; | emnlp | 2020-11-12 |
| 381 | Hierarchical Graph Network For Multi-hop Question Answering IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. |
YUWEI FANG et. al. | emnlp | 2020-11-12 |
| 382 | Training Question Answering Models From Synthetic Data IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work aims to narrow this gap by taking advantage of large language models and explores several factors such as model size, quality of pretrained models, scale of data synthesized, and algorithmic choices. |
Raul Puri; Ryan Spring; Mohammad Shoeybi; Mostofa Patwary; Bryan Catanzaro; | emnlp | 2020-11-12 |
| 383 | HERO: Hierarchical Encoder For Video+Language Omni-representation Pre-training IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present HERO, a novel framework for large-scale video+language omni-representation learning. |
LINJIE LI et. al. | emnlp | 2020-11-12 |
| 384 | Exploring Contextualized Neural Language Models For Temporal Dependency Parsing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop several variants of BERT-based temporal dependency parser, and show that BERT significantly improves temporal dependency parsing (Zhang and Xue, 2018a). |
Hayley Ross; Jonathon Cai; Bonan Min; | emnlp | 2020-11-12 |
| 385 | Learning To Contrast The Counterfactual Samples For Robust Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we introduce a novel self-supervised contrastive learning mechanism to learn the relationship between original samples, factual samples and counterfactual samples. |
Zujie Liang; Weitao Jiang; Haifeng Hu; Jiaying Zhu; | emnlp | 2020-11-12 |
| 386 | From Zero To Hero: On The Limitations Of Zero-Shot Language Transfer With Multilingual Transformers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze the limitations of downstream language transfer with MMTs, showing that, much like cross-lingual word embeddings, they are substantially less effective in resource-lean scenarios and for distant languages. |
Anne Lauscher; Vinit Ravishankar; Ivan Vulić; Goran Glavaš; | emnlp | 2020-11-12 |
| 387 | A Simple Yet Strong Pipeline For HotpotQA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our pipeline has three steps: 1) use BERT to identify potentially relevant sentences \textit{independently} of each other; 2) feed the set of selected sentences as context into a standard BERT span prediction model to choose an answer; and 3) use the sentence selection model, now with the chosen answer, to produce supporting sentences. |
Dirk Groeneveld; Tushar Khot; Mausam; Ashish Sabharwal; | emnlp | 2020-11-12 |
| 388 | STL-CQA: Structure-based Transformers With Localization And Encoding For Chart Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose STL-CQA which improves the question/answering through sequential elements localization, question encoding and then, a structural transformer-based learning approach. |
Hrituraj Singh; Sumit Shekhar; | emnlp | 2020-11-12 |
| 389 | QADiscourse – Discourse Relations As QA Pairs: Representation, Crowdsourcing And Baselines IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel representation of discourse relations as QA pairs, which in turn allows us to crowd-source wide-coverage data annotated with discourse relations, via an intuitively appealing interface for composing such questions and answers. |
Valentina Pyatkin; Ayal Klein; Reut Tsarfaty; Ido Dagan; | emnlp | 2020-11-12 |
| 390 | A Survey On Recent Advances In Sequence Labeling From Deep Learning Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to present a comprehensive review of existing deep learning-based sequence labeling models, which consists of three related tasks, e.g., part-of-speech tagging, named entity recognition, and text chunking. Then, we systematically present the existing approaches base on a scientific taxonomy, as well as the widely-used experimental datasets and popularly-adopted evaluation metrics in the SL domain. |
ZHIYONG HE et. al. | arxiv-cs.CL | 2020-11-12 |
| 391 | Does My Multimodal Model Learn Cross-modal Interactions? It’s Harder To Tell Than You Might Think! IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new diagnostic tool, empirical multimodally-additive function projection (EMAP), for isolating whether or not cross-modal interactions improve performance for a given model on a given task. |
Jack Hessel; Lillian Lee; | emnlp | 2020-11-12 |
| 392 | ProtoQA: A Question Answering Dataset For Prototypical Common-Sense Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a new question answering dataset for training and evaluating common sense reasoning capabilities of artificial intelligence systems in such prototypical situations. |
MICHAEL BORATKO et. al. | emnlp | 2020-11-12 |
| 393 | Event Extraction As Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new learning paradigm of EE, by explicitly casting it as a machine reading comprehension problem (MRC). |
Jian Liu; Yubo Chen; Kang Liu; Wei Bi; Xiaojiang Liu; | emnlp | 2020-11-12 |
| 394 | T3: Tree-Autoencoder Constrained Adversarial Text Generation For Targeted Attack IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To handle these challenges, we propose a target-controllable adversarial attack framework T3, which is applicable to a range of NLP tasks. |
BOXIN WANG et. al. | emnlp | 2020-11-12 |
| 395 | Generating Fact Checking Briefs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To train its components, we introduce QABriefDataset We show that fact checking with briefs – in particular QABriefs – increases the accuracy of crowdworkers by 10% while slightly decreasing the time taken. |
ANGELA FAN et. al. | emnlp | 2020-11-12 |
| 396 | Universal Natural Language Processing With Limited Annotations: Try Few-shot Textual Entailment As A Start IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce Universal Few-shot textual Entailment (UFO-Entail). |
Wenpeng Yin; Nazneen Fatema Rajani; Dragomir Radev; Richard Socher; Caiming Xiong; | emnlp | 2020-11-12 |
| 397 | Improving Multilingual Models With Language-Clustered Vocabularies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a novel procedure for multilingual vocabulary generation that combines the separately trained vocabularies of several automatically derived language clusters, thus balancing the trade-off between cross-lingual subword sharing and language-specific vocabularies. |
Hyung Won Chung; Dan Garrette; Kiat Chuan Tan; Jason Riesa; | emnlp | 2020-11-12 |
| 398 | EXAMS: A Multi-subject High School Examinations Dataset For Cross-lingual And Multilingual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose EXAMS – a new benchmark dataset for cross-lingual and multilingual question answering for high school examinations. |
MOMCHIL HARDALOV et. al. | emnlp | 2020-11-12 |
| 399 | AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. |
Silei Xu; Sina Semnani; Giovanni Campagna; Monica Lam; | emnlp | 2020-11-12 |
| 400 | Video2Commonsense: Generating Commonsense Descriptions To Enrich Video Captioning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the first work on generating \textit{commonsense} captions directly from videos, to describe latent aspects such as intentions, effects, and attributes. |
Zhiyuan Fang; Tejas Gokhale; Pratyay Banerjee; Chitta Baral; Yezhou Yang; | emnlp | 2020-11-12 |
| 401 | Infusing Disease Knowledge Into BERT For Health Question Answering, Medical Inference And Disease Name Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we propose a new disease knowledge infusion training procedure and evaluate it on a suite of BERT models including BERT, BioBERT, SciBERT, ClinicalBERT, BlueBERT, and ALBERT. |
Yun He; Ziwei Zhu; Yin Zhang; Qin Chen; James Caverlee; | emnlp | 2020-11-12 |
| 402 | Don’t Read Too Much Into It: Adaptive Computation For Open-Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reduce this cost, we propose the use of adaptive computation to control the computational budget allocated for the passages to be read. |
Yuxiang Wu; Sebastian Riedel; Pasquale Minervini; Pontus Stenetorp; | emnlp | 2020-11-12 |
| 403 | BioMegatron: Larger Biomedical Domain Language Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We empirically study and evaluate several factors that can affect performance on domain language applications, such as the sub-word vocabulary set, model size, pre-training corpus, and domain transfer. |
HOO-CHANG SHIN et. al. | emnlp | 2020-11-12 |
| 404 | Methods For Numeracy-Preserving Word Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new methodology to assign and learn embeddings for numbers. |
DHANASEKAR SUNDARARAMAN et. al. | emnlp | 2020-11-12 |
| 405 | Learning A Cost-Effective Annotation Policy For Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a remedy, we propose a novel framework for annotating QA datasets that entails learning a cost-effective annotation policy and a semi-supervised annotation scheme. |
Bernhard Kratzwald; Stefan Feuerriegel; Huan Sun; | emnlp | 2020-11-12 |
| 406 | How Do Decisions Emerge Across Layers In Neural Models? Interpretation With Differentiable Masking IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To deal with these challenges, we introduce Differentiable Masking. |
Nicola De Cao; Michael Sejr Schlichtkrull; Wilker Aziz; Ivan Titov; | emnlp | 2020-11-12 |
| 407 | Tell Me How To Ask Again: Question Data Augmentation With Controllable Rewriting In Continuous Space IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC), question generation, and question-answering natural language inference tasks. |
DAYIHENG LIU et. al. | emnlp | 2020-11-12 |
| 408 | Unsupervised Adaptation Of Question Answering Systems Via Generative Self-training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we investigate the iterative generation of synthetic QA pairs as a way to realize unsupervised self adaptation. |
Steven Rennie; Etienne Marcheret; Neil Mallinar; David Nahamoo; Vaibhava Goel; | emnlp | 2020-11-12 |
| 409 | Self-Supervised Knowledge Triplet Learning For Zero-Shot Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes Knowledge Triplet Learning (KTL), a self-supervised task over knowledge graphs. |
Pratyay Banerjee; Chitta Baral; | emnlp | 2020-11-12 |
| 410 | Knowledge-guided Open Attribute Value Extraction With Reinforcement Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a knowledge-guided reinforcement learning (RL) framework for open attribute value extraction. |
Ye Liu; Sheng Zhang; Rui Song; Suo Feng; Yanghua Xiao; | emnlp | 2020-11-12 |
| 411 | Exploiting Structured Knowledge In Text Via Graph-Guided Representation Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim at equipping pre-trained language models with structured knowledge. |
TAO SHEN et. al. | emnlp | 2020-11-12 |
| 412 | Scalable Multi-Hop Relational Reasoning For Knowledge-Aware Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel knowledge-aware approach that equips pre-trained language models (PTLMs) has with a multi-hop relational reasoning module, named multi-hop graph relation network (MHGRN). |
YANLIN FENG et. al. | emnlp | 2020-11-12 |
| 413 | SubjQA: A Dataset For Subjectivity And Review Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We find that subjectivity is an important feature in the case of QA, albeit with more intricate interactions between subjectivity and QA performance than found in previous work on sentiment analysis. We develop a new dataset which allows us to investigate this relationship. |
Johannes Bjerva; Nikita Bhutani; Behzad Golshan; Wang-Chiew Tan; Isabelle Augenstein; | emnlp | 2020-11-12 |
| 414 | CapWAP: Image Captioning With A Purpose IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new task, Captioning with A Purpose (CapWAP). |
Adam Fisch; Kenton Lee; Ming-Wei Chang; Jonathan Clark; Regina Barzilay; | emnlp | 2020-11-12 |
| 415 | A Supervised Word Alignment Method Based On Cross-Language Span Prediction Using Multilingual BERT IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel supervised word alignment method based on cross-language span prediction. |
Masaaki Nagata; Katsuki Chousa; Masaaki Nishino; | emnlp | 2020-11-12 |
| 416 | F1 Is Not Enough! Models And Evaluation Towards User-Centered Explainable Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a remedy, we propose a hierarchical model and a new regularization term to strengthen the answer-explanation coupling as well as two evaluation scores to quantify the coupling. |
Hendrik Schuff; Heike Adel; Ngoc Thang Vu; | emnlp | 2020-11-12 |
| 417 | BERT Knows Punta Cana Is Not Just Beautiful, It’s Gorgeous: Ranking Scalar Adjectives With Contextualised Representations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel BERT-based approach to intensity detection for scalar adjectives. |
Aina Garí Soler; Marianna Apidianaki; | emnlp | 2020-11-12 |
| 418 | Multi-hop Inference For Question-driven Summarization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel question-driven abstractive summarization method, Multi-hop Selective Generator (MSG), to incorporate multi-hop reasoning into question-driven summarization and, meanwhile, provide justifications for the generated summaries. |
Yang Deng; Wenxuan Zhang; Wai Lam; | emnlp | 2020-11-12 |
| 419 | AnswerFact: Fact Checking In Product Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this issue, we investigate to predict the veracity of answers in this paper and introduce AnswerFact, a large scale fact checking dataset from product question answering forums. |
Wenxuan Zhang; Yang Deng; Jing Ma; Wai Lam; | emnlp | 2020-11-12 |
| 420 | Zero-Shot Cross-Lingual Transfer With Meta Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that this challenging setup can be approached using meta-learning: in addition to training a source language model, another model learns to select which training instances are the most beneficial to the first. |
Farhad Nooralahzadeh; Giannis Bekoulis; Johannes Bjerva; Isabelle Augenstein; | emnlp | 2020-11-12 |
| 421 | ISAAQ – Mastering Textbook Questions With Pre-trained Transformers And Bottom-Up And Top-Down Attention IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For the first time, this paper taps on the potential of transformer language models and bottom-up and top-down attention to tackle the language and visual understanding challenges this task entails. |
Jose Manuel Gomez-Perez; Raúl Ortega; | emnlp | 2020-11-12 |
| 422 | End-to-End Synthetic Data Generation For Domain Adaptation Of Question Answering Systems IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an end-to-end approach for synthetic QA data generation. |
SIAMAK SHAKERI et. al. | emnlp | 2020-11-12 |
| 423 | Efficient Meta Lifelong-Learning With Limited Memory IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we identify three common principles of lifelong learning methods and propose an efficient meta-lifelong framework that combines them in a synergistic fashion. |
Zirui Wang; Sanket Vaibhav Mehta; Barnabas Poczos; Jaime Carbonell; | emnlp | 2020-11-12 |
| 424 | Context-Aware Answer Extraction In Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve this issue, we propose BLANC (BLock AttentioN for Context prediction) based on two main ideas: context prediction as an auxiliary task in multi-task learning manner, and a block attention method that learns the context prediction task. |
Yeon Seonwoo; Ji-Hoon Kim; Jung-Woo Ha; Alice Oh; | emnlp | 2020-11-12 |
| 425 | Biomedical Named Entity Recognition At Scale IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Reimplementing a Bi-LSTM-CNN-Char deep learning architecture on top of Apache Spark, we present a single trainable NER model that obtains new state-of-the-art results on seven public biomedical benchmarks without using heavy contextual embeddings like BERT. |
Veysel Kocaman; David Talby; | arxiv-cs.CL | 2020-11-12 |
| 426 | Exploring And Predicting Transferability Across NLP Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct an extensive study of the transferability between 33 NLP tasks across three broad classes of problems (text classification, question answering, and sequence labeling). |
TU VU et. al. | emnlp | 2020-11-12 |
| 427 | LUKE: Deep Contextualized Entity Representations With Entity-aware Self-attention IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. |
Ikuya Yamada; Akari Asai; Hiroyuki Shindo; Hideaki Takeda; Yuji Matsumoto; | emnlp | 2020-11-12 |
| 428 | Multi-Fact Correction In Abstractive Text Summarization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose Span-Fact, a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. |
YUE DONG et. al. | emnlp | 2020-11-12 |
| 429 | Exposing Shallow Heuristics Of Relation Extraction Models With Challenge Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify failure modes of SOTA relation extraction (RE) models trained on TACRED, which we attribute to limitations in the data annotation process. |
Shachar Rosenman; Alon Jacovi; Yoav Goldberg; | emnlp | 2020-11-12 |
| 430 | X-LXMERT: Paint, Caption And Answer Questions With Multi-Modal Transformers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce X-LXMERT, an extension to LXMERT with training refinements including: discretizing visual representations, using uniform masking with a large range of masking ratios and aligning the right pre-training datasets to the right objectives which enables it to paint. |
Jaemin Cho; Jiasen Lu; Dustin Schwenk; Hannaneh Hajishirzi; Aniruddha Kembhavi; | emnlp | 2020-11-12 |
| 431 | More Bang For Your Buck: Natural Perturbation For Robust Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As an alternative to the traditional approach of creating new instances by repeating the process of creating one instance, we propose doing so by first collecting a set of seed examples and then applying human-driven natural perturbations (as opposed to rule-based machine perturbations), which often change the gold label as well. |
Daniel Khashabi; Tushar Khot; Ashish Sabharwal; | emnlp | 2020-11-12 |
| 432 | MOCHA: A Dataset For Training And Evaluating Generative Reading Comprehension Metrics IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we introduce a benchmark for training and evaluating generative reading comprehension metrics: MOdeling Correctness with Human Annotations. |
Anthony Chen; Gabriel Stanovsky; Sameer Singh; Matt Gardner; | emnlp | 2020-11-12 |
| 433 | Cross-Thought For Sentence Encoder Pre-training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering. |
SHUOHANG WANG et. al. | emnlp | 2020-11-12 |
| 434 | Coarse-to-Fine Query Focused Multi-Document Summarization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a coarse-to-fine modeling framework which employs progressively more accurate modules for estimating whether text segments are relevant, likely to contain an answer, and central. |
Yumo Xu; Mirella Lapata; | emnlp | 2020-11-12 |
| 435 | Learning To Explain: Datasets And Models For Identifying Valid Reasoning Chains In Multihop Question-Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we introduce three explanation datasets in which explanations formed from corpus facts are annotated. |
Harsh Jhamtani; Peter Clark; | emnlp | 2020-11-12 |
| 436 | On The Importance Of Pre-training Data Volume For Compact Language Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In an effort towards sustainable practices, we study the impact of pre-training data volume on compact language models. |
Vincent Micheli; Martin d’Hoffschmidt; François Fleuret; | emnlp | 2020-11-12 |
| 437 | Few-Shot Complex Knowledge Base Question Answering Via Meta Reinforcement Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a meta-reinforcement learning approach to program induction in CQA to tackle the potential distributional bias in questions. |
Yuncheng Hua; Yuan-Fang Li; Gholamreza Haffari; Guilin Qi; Tongtong Wu; | emnlp | 2020-11-12 |
| 438 | Localizing Open-Ontology QA Semantic Parsers In A Day Using Machine Translation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language. |
Mehrad Moradshahi; Giovanni Campagna; Sina Semnani; Silei Xu; Monica Lam; | emnlp | 2020-11-12 |
| 439 | MUTANT: A Training Paradigm For Out-of-Distribution Generalization In Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present \textit{MUTANT}, a training paradigm that exposes the model to perceptually similar, yet semantically distinct \textit{mutations} of the input, to improve OOD generalization, such as the VQA-CP challenge. |
Tejas Gokhale; Pratyay Banerjee; Chitta Baral; Yezhou Yang; | emnlp | 2020-11-12 |
| 440 | Neural Mask Generator: Learning To Generate Adaptive Word Maskings For Language Model Adaptation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method to automatically generate a domain- and task-adaptive maskings of the given text for self-supervised pre-training, such that we can effectively adapt the language model to a particular target task (e.g. question answering). |
Minki Kang; Moonsu Han; Sung Ju Hwang; | emnlp | 2020-11-12 |
| 441 | Efficient One-Pass End-to-End Entity Linking For Questions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ELQ, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass. |
Belinda Z. Li; Sewon Min; Srinivasan Iyer; Yashar Mehdad; Wen-tau Yih; | emnlp | 2020-11-12 |
| 442 | BiST: Bi-directional Spatio-Temporal Reasoning For Video-Grounded Dialogues IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this drawback, we proposed Bi-directional Spatio-Temporal Learning (BiST), a vision-language neural framework for high-resolution queries in videos based on textual cues. |
Hung Le; Doyen Sahoo; Nancy Chen; Steven C.H. Hoi; | emnlp | 2020-11-12 |
| 443 | PRover: Proof Generation For Interpretable Reasoning Over Rules IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our work, we take a step closer to emulating formal theorem provers, by proposing PRover, an interpretable transformer-based model that jointly answers binary questions over rule-bases and generates the corresponding proofs. |
Swarnadeep Saha; Sayan Ghosh; Shashank Srivastava; Mohit Bansal; | emnlp | 2020-11-12 |
| 444 | Towards Interpreting BERT For Reading Comprehension Based QA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we attempt to interpret BERT for RCQA. |
Sahana Ramnath; Preksha Nema; Deep Sahni; Mitesh M. Khapra; | emnlp | 2020-11-12 |
| 445 | What Do Models Learn From Question Answering Datasets? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate if models are learning reading comprehension from QA datasets by evaluating BERT-based models across five datasets. |
Priyanka Sen; Amir Saffari; | emnlp | 2020-11-12 |
| 446 | Is Graph Structure Necessary For Multi-hop Question Answering? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate whether the graph structure is necessary for textual multi-hop reasoning. |
Nan Shao; Yiming Cui; Ting Liu; Shijin Wang; Guoping Hu; | emnlp | 2020-11-12 |
| 447 | Compositional And Lexical Semantics In RoBERTa, BERT And DistilBERT: A Case Study On CoQA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify the problematic areas for the finetuned RoBERTa, BERT and DistilBERT models through systematic error analysis – basic arithmetic (counting phrases), compositional semantics (negation and Semantic Role Labeling), and lexical semantics (surprisal and antonymy). |
Ieva Staliūnaitė; Ignacio Iacobacci; | emnlp | 2020-11-12 |
| 448 | Neural Conversational QA: Learning To Reason Vs Exploiting Patterns Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we share our findings about the four types of patterns in the ShARC corpus and how the neural models exploit them. |
NIKHIL VERMA et. al. | emnlp | 2020-11-12 |
| 449 | MultiCQA: Zero-Shot Transfer Of Self-Supervised Text Matching Models On A Massive Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to incorporate self-supervised with supervised multi-task learning on all available source domains. |
Andreas Rücklé; Jonas Pfeiffer; Iryna Gurevych; | emnlp | 2020-11-12 |
| 450 | PALM: Pre-training An Autoencoding&Autoregressive Language Model For Context-conditioned Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus, specifically designed for generating new text conditioned on context. |
BIN BI et. al. | emnlp | 2020-11-12 |
| 451 | LIAF-Net: Leaky Integrate And Analog Fire Network For Lightweight And Efficient Spatiotemporal Information Processing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, in this work, we propose a Leaky Integrate and Analog Fire (LIAF) neuron model, so that analog values can be transmitted among neurons, and a deep network termed as LIAF-Net is built on it for efficient spatiotemporal processing. |
ZHENZHI WU et. al. | arxiv-cs.LG | 2020-11-11 |
| 452 | HybridQA: A Dataset Of Multi-Hop Question Answering Over Tabular And Textual Data IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill in the gap, we present HybridQA, a new large-scale question-answering dataset that requires reasoning on heterogeneous information. |
WENHU CHEN et. al. | emnlp | 2020-11-10 |
| 453 | UnifiedQA: Crossing Format Boundaries With A Single QA System IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As evidence, we use the latest advances in language modeling to build a single pre-trained QA model, UNIFIEDQA, that performs well across 19 QA datasets spanning 4 diverse formats. |
DANIEL KHASHABI et. al. | emnlp | 2020-11-10 |
| 454 | Blockwise Self-Attention For Long Document Understanding IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present BlockBERT, a lightweight and efficient BERT model for better modeling long-distance dependencies. |
JIEZHONG QIU et. al. | emnlp | 2020-11-10 |
| 455 | Gradient-based Analysis Of NLP Models Is Manipulable IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, however, we demonstrate that the gradients of a model are easily manipulable, and thus bring into question the reliability of gradient-based analyses. |
Junlin Wang; Jens Tuyls; Eric Wallace; Sameer Singh; | emnlp | 2020-11-10 |
| 456 | Event Extraction As Multi-turn Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a new paradigm that formulates event extraction as multi-turn question answering. |
FAYUAN LI et. al. | emnlp | 2020-11-10 |
| 457 | Understanding Tables With Intermediate Pre-training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We adapt TAPAS (Herzig et al., 2020), a table-based BERT model, to recognize entailment. Motivated by the benefits of data augmentation, we create a balanced dataset of millions of automatically created training examples which are learned in an intermediate step prior to fine-tuning. |
Julian Eisenschlos; Syrine Krichene; Thomas Müller; | emnlp | 2020-11-10 |
| 458 | Visuo-Lingustic Question Answering (VLQA) Challenge IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel task to derive joint inference about a given image-text modality and compile the Visuo-Linguistic Question Answering (VLQA) challenge corpus in a question answering setting. |
Shailaja Keyur Sampat; Yezhou Yang; Chitta Baral; | emnlp | 2020-11-10 |
| 459 | E-BERT: Efficient-Yet-Effective Entity Embeddings For BERT IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel way of injecting factual knowledge about entities into the pretrained BERT model (Devlin et al., 2019): We align Wikipedia2Vec entity vectors (Yamada et al., 2016) with BERT’s native wordpiece vector space and use the aligned entity vectors as if they were wordpiece vectors. |
Nina Poerner; Ulli Waltinger; Hinrich Schütze; | emnlp | 2020-11-10 |
| 460 | PolicyQA: A Reading Comprehension Dataset For Privacy Policies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present PolicyQA, a dataset that contains 25,017 reading comprehension style examples curated from an existing corpus of 115 website privacy policies. |
Wasi Ahmad; Jianfeng Chi; Yuan Tian; Kai-Wei Chang; | emnlp | 2020-11-10 |
| 461 | Medical Knowledge-enriched Textual Entailment Framework IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel Medical Knowledge-Enriched Textual Entailment framework that allows the model to acquire a semantic and global representation of the input medical text with the help of a relevant domain-specific knowledge graph. |
Shweta Yadav; Vishal Pallagani; Amit Sheth; | arxiv-cs.CL | 2020-11-10 |
| 462 | Question Answering With Long Multiple-Span Answers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document. |
Ming Zhu; Aman Ahuja; Da-Cheng Juan; Wei Wei; Chandan K. Reddy; | emnlp | 2020-11-10 |
| 463 | BERT-kNN: Adding A KNN Search Component To Pretrained Language Models For Better QA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our contributions are as follows: i) BERT-kNN outperforms BERT on cloze-style QA by large margins without any further training. |
Nora Kassner; Hinrich Schütze; | emnlp | 2020-11-10 |
| 464 | Improve Transformer Models With Better Relative Position Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that the position information is not fully utilized in existing work. |
Zhiheng Huang; Davis Liang; Peng Xu; Bing Xiang; | emnlp | 2020-11-10 |
| 465 | Open-Ended Visual Question Answering By Multi-Modal Domain Adaptation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the above issues by proposing a novel supervised multi-modal domain adaptation method for VQA to learn joint feature embeddings across different domains and modalities. |
Yiming Xu; Lin Chen; Zhongwei Cheng; Lixin Duan; Jiebo Luo; | emnlp | 2020-11-10 |
| 466 | Beyond Language: Learning Commonsense From Images For Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in NLP. |
Wanqing Cui; Yanyan Lan; Liang Pang; Jiafeng Guo; Xueqi Cheng; | emnlp | 2020-11-10 |
| 467 | On The Importance Of Adaptive Data Collection For Extremely Imbalanced Pairwise Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We instead collect training data with active learning, using a BERT-based embedding model to efficiently retrieve uncertain points from a very large pool of unlabeled utterance pairs. |
Stephen Mussmann; Robin Jia; Percy Liang; | emnlp | 2020-11-10 |
| 468 | Open Domain Question Answering Based On Text Enhanced Knowledge Graph With Hyperedge Infusion IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel QA method by leveraging text information to enhance the incomplete KB. |
Jiale Han; Bo Cheng; Xu Wang; | emnlp | 2020-11-10 |
| 469 | Pushing The Limits Of AMR Parsing With Self-Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore different ways in which trained models can be applied to improve AMR parsing performance, including generation of synthetic text and AMR annotations as well as refinement of actions oracle. |
YOUNG-SUK LEE et. al. | emnlp | 2020-11-10 |
| 470 | Pragmatic Issue-Sensitive Image Captioning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose Issue-Sensitive Image Captioning (ISIC). |
Allen Nie; Reuben Cohn-Gordon; Christopher Potts; | emnlp | 2020-11-10 |
| 471 | Regularization Of Distinct Strategies For Unsupervised Question Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel regularization method based on teacher-student architecture to avoid bias toward a particular question generation strategy and modulate the process of generating individual words when a question is generated. |
Junmo Kang; Giwon Hong; Haritz Puerto San Roman; Sung-Hyon Myaeng; | emnlp | 2020-11-10 |
| 472 | Natural Language Rationales With Full-Stack Visual Reasoning: From Pixels To Semantic Frames To Commonsense Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Rationale{\^{}}VT Transformer, an integrated model that learns to generate free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs. |
ANA MARASOVIĆ et. al. | emnlp | 2020-11-10 |
| 473 | Improving QA Generalization By Concurrent Modeling Of Multiple Biases IF:2 Related Papers |