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 | Visual Question Answering Based on Local-Scene-Aware Referring Expression Generation 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 |
| 2 | MultiModalQA: Complex Question Answering Over Text, Tables and Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: MultiModalQA: A question answering dataset that requires multi-modal multi-hop reasoning over wikipedia text, tables and images, accompanied by a new multi-hop model for tackling the task. |
ALON TALMOR et. al. | iclr | 2021-01-21 |
| 3 | 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 |
| 4 | Learning to Deceive Knowledge Graph Augmented Models Via Targeted Perturbation 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 |
| 5 | Open Question Answering Over Tables and Text 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 |
| 6 | Contextual Dropout: An Efficient Sample-Dependent Dropout Module Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose contextual dropout as a scalable sample-dependent dropout method, which makes the dropout probabilities depend on the input covariates of each data sample. |
XINJIE FAN; Shujian Zhang; Korawat Tanwisuth; Xiaoning Qian; Mingyuan Zhou; | iclr | 2021-01-21 |
| 7 | Fast Clustering of Short Text Streams Using Efficient Cluster Indexing and Dynamic Similarity Thresholds 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 |
| 8 | Distilling Knowledge from Reader to Retriever for Question Answering 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 |
| 9 | Iterated Learning for Emergent Systematicity in VQA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We use iterated learning to encourage the emergence of structure in the generated programs for neural module networks. |
Ankit Vani; Max Schwarzer; Yuchen Lu; Eeshan Dhekane; Aaron Courville; | iclr | 2021-01-21 |
| 10 | Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel post-hoc interpretation method for graph neural networks, and apply it to analyse two models from the NLP literature. |
Michael Sejr Schlichtkrull; Nicola De Cao; Ivan Titov; | iclr | 2021-01-21 |
| 11 | Autoregressive Entity Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address entity retrieval by generating their unique name identifiers, left to right, in an autoregressive fashion, and conditioned on the context showing SOTA results in more than 20 datasets with a tiny fraction of the memory of recent systems. |
Nicola De Cao; Gautier Izacard; Sebastian Riedel; Fabio Petroni; | iclr | 2021-01-21 |
| 12 | InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel learning framework, InfoBERT, for robust fine-tuning of pre-trained language models from an information-theoretic perspective, and achieve state-of-the-art robust accuracy over several adversarial datasets on NLI and QA tasks. |
BOXIN WANG et. al. | iclr | 2021-01-21 |
| 13 | Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval 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 |
| 14 | Disentangling 3D Prototypical Networks for Few-Shot Concept Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present neural architectures that disentangle RGB-D images into objects? shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification. |
MIHIR PRABHUDESAI et. al. | iclr | 2021-01-21 |
| 15 | Zero-shot Generalization in Dialog State Tracking Through Generative Question Answering 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 |
| 16 | Towards Confident Machine Reading Comprehension 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 |
| 17 | Tip of The Tongue Known-Item Retrieval: A Case Study in Movie Identification 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 |
| 18 | Mitigating The Position Bias of Transformer Models in Passage Re-Ranking 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 |
| 19 | Incremental Knowledge Based Question Answering 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 |
| 20 | 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 |
| 21 | HySTER: A Hybrid Spatio-Temporal Event Reasoner 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 |
| 22 | Understanding in Artificial Intelligence 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 |
| 23 | Latent Variable Models for Visual Question Answering 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 |
| 24 | 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 |
| 25 | Match-Ignition: Plugging PageRank Into Transformer for Long-form Text Matching 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 |
| 26 | Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC 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 |
| 27 | Coarse-grained Decomposition and Fine-grained Interaction for Multi-hop Question Answering 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 |
| 28 | Reasoning Over Vision and Language: Exploring The Benefits of Supplemental Knowledge 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 |
| 29 | Recent Advances in Video Question Answering: A Review of Datasets and Methods 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 |
| 30 | Understanding The Role of Scene Graphs in Visual Question Answering 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 |
| 31 | Neural Sequence-to-grid Module for Learning Symbolic Rules 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 |
| 32 | 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 |
| 33 | Predicting Relative Depth Between Objects from Semantic Features 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 |
| 34 | A Neural Question Answering System for Basic Questions About Subroutines 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 |
| 35 | Improving Multi-hop Knowledge Base Question Answering By Learning Intermediate Supervision Signals 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 |
| 36 | Explain and Predict, and Then Predict Again 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 |
| 37 | Learning Better Sentence Representation with Syntax Information 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 |
| 38 | A Novel Word Sense Disambiguation Approach Using WordNet Knowledge Graph 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 |
| 39 | Did Aristotle Use A Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies 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 |
| 40 | Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity 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 |
| 41 | EfficientQA : A RoBERTa Based Phrase-Indexed Question-Answering System 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; | arxiv-cs.CL | 2021-01-06 |
| 42 | SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering 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 |
| 43 | Modeling Global Semantics for Question Answering Over Knowledge Bases 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 |
| 44 | End-to-End Video Question-Answer Generation with Generator-Pretester Network 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 |
| 45 | Personalized Food Recommendation As Constrained Question Answering Over A Large-scale Food Knowledge Graph 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 |
| 46 | Coreference Resolution In Research Papers From Multiple Domains 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 |
| 47 | Transformers In Vision: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering and visual reasoning), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution and colorization) and 3D analysis (e.g., point cloud classification and segmentation). |
SALMAN KHAN et. al. | arxiv-cs.CV | 2021-01-04 |
| 48 | Retrieving And Reading: A Comprehensive Survey On Open-domain Question Answering 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 |
| 49 | Benchmarking Knowledge-Enhanced Commonsense Question Answering Via Knowledge-to-Text Transformation 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 |
| 50 | Few-Shot Question Answering By Pretraining Span Selection 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 |
| 51 | Which Linguist Invented The Lightbulb? Presupposition Verification For Question-Answering 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 |
| 52 | RiddleSense: Answering Riddle Questions As Commonsense Reasoning 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 |
| 53 | End-to-End Training Of Neural Retrievers For Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we systematically study retriever pre-training. |
DEVENDRA SINGH SACHAN et. al. | arxiv-cs.CL | 2021-01-02 |
| 54 | UnitedQA: A Hybrid Approach For Open Domain Question Answering 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 |
| 55 | Reader-Guided Passage Reranking For Open-Domain Question Answering 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 |
| 56 | 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 |
| 57 | Coreference Reasoning In Machine Reading Comprehension 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 |
| 58 | Studying Strategically: Learning To Mask For Closed-book QA 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 |
| 59 | HopRetriever: Retrieve Hops Over Wikipedia To Answer Complex Questions 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 |
| 60 | NeurIPS 2020 EfficientQA Competition: Systems, Analyses And Lessons Learned 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 |
| 61 | Multi-task Retrieval For Knowledge-Intensive Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Driven by the question of whether a neural retrieval model can be universal and perform robustly on a wide variety of problems, we propose a multi-task trained model. |
JEAN MAILLARD et. al. | arxiv-cs.CL | 2020-12-31 |
| 62 | Seeing Is Knowing! Fact-based Visual Question Answering Using Knowledge Graph Embeddings 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 |
| 63 | FiD-Ex: Improving Sequence-to-Sequence Models For Extractive Rationale Generation 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 |
| 64 | ERNIE-DOC: The Retrospective Long-Document Modeling Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ERNIE-DOC, a document-level language pretraining model based on Recurrence Transformers. |
SIYU DING et. al. | arxiv-cs.CL | 2020-12-31 |
| 65 | An Experimental Evaluation Of Transformer-based Language Models In The Biomedical Domain 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 |
| 66 | 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 |
| 67 | 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 |
| 68 | 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 |
| 69 | Causal Perception in Question-Answering Systems 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 |
| 70 | Red Dragon AI At TextGraphs 2020 Shared Task: LIT : LSTM-Interleaved Transformer For Multi-Hop Explanation Ranking 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 |
| 71 | 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 |
| 72 | 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 |
| 73 | 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 |
| 74 | 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 |
| 75 | 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 |
| 76 | 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 |
| 77 | 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 |
| 78 | 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 |
| 79 | 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 |
| 80 | Learning Content And Context With Language Bias For Visual Question Answering IF:2 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 |
| 81 | Object-Centric Diagnosis Of Visual Reasoning IF:2 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 |
| 82 | 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 |
| 83 | 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 |
| 84 | 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 |
| 85 | 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 |
| 86 | 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 |
| 87 | 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 |
| 88 | 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 |
| 89 | Knowledge-Routed Visual Question Reasoning: Challenges For Deep Representation Embedding 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 |
| 90 | 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 |
| 91 | 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 |
| 92 | 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 |
| 93 | 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 |
| 94 | 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 |
| 95 | 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 |
| 96 | 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 |
| 97 | 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 |
| 98 | 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 |
| 99 | 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 |
| 100 | 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 |
| 101 | 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 |
| 102 | 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 to learn video question answering (VideoQA) from millions of readily-available narrated videos. Finally, for a detailed evaluation we introduce a new manually annotated VideoQA dataset with reduced language biases and high quality annotations. |
Antoine Yang; Antoine Miech; Josef Sivic; Ivan Laptev; Cordelia Schmid; | arxiv-cs.CV | 2020-12-01 |
| 103 | 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 |
| 104 | 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 |
| 105 | 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 |
| 106 | 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 |
| 107 | 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 |
| 108 | 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 |
| 109 | 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 |
| 110 | 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 |
| 111 | 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 |
| 112 | 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 |
| 113 | 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 |
| 114 | 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 |
| 115 | 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 |
| 116 | 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 |
| 117 | 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 |
| 118 | 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 |
| 119 | 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 |
| 120 | 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 |
| 121 | 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 |
| 122 | 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 |
| 123 | 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 |
| 124 | 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 |
| 125 | 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 |
| 126 | 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 |
| 127 | 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 |
| 128 | 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 |
| 129 | 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 |
| 130 | Language Models Are Few-Shot Learners IF:6 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 |
| 131 | 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 |
| 132 | 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 |
| 133 | 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 |
| 134 | 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 |
| 135 | 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 |
| 136 | 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 |
| 137 | Efficient Distance Approximation For Structured High-Dimensional Distributions Via Learning 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 |
| 138 | Sparse And Continuous Attention Mechanisms 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 |
| 139 | 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 |
| 140 | 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 |
| 141 | Faithful Embeddings For Knowledge Base Queries 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 |
| 142 | Removing Bias In Multi-modal Classifiers: Regularization By Maximizing Functional Entropies 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 |
| 143 | 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 |
| 144 | Pushing The Limits Of Narrow Precision Inferencing At Cloud Scale With Microsoft Floating Point 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 |
| 145 | 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 |
| 146 | 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 |
| 147 | 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 |
| 148 | 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 |
| 149 | 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 |
| 150 | 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 |
| 151 | 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 |
| 152 | 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 |
| 153 | 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 |
| 154 | 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 |
| 155 | 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 |
| 156 | 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 |
| 157 | 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 |
| 158 | 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 |
| 159 | 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 |
| 160 | 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 |
| 161 | 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 |
| 162 | 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 |
| 163 | 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 |
| 164 | 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 |
| 165 | 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 |
| 166 | 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 |
| 167 | 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 |
| 168 | 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 |
| 169 | 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 |
| 170 | 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 |
| 171 | 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 |
| 172 | MultiCQA: Zero-Shot Transfer Of Self-Supervised Text Matching Models On A Massive Scale IF:2 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 |
| 173 | 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 |
| 174 | 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 |
| 175 | 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 |
| 176 | Look At The First Sentence: Position Bias In Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we hypothesize that when the distribution of the answer positions is highly skewed in the training set (e.g., answers lie only in the k-th sentence of each passage), QA models predicting answers as positions can learn spurious positional cues and fail to give answers in different positions. |
Miyoung Ko; Jinhyuk Lee; Hyunjae Kim; Gangwoo Kim; Jaewoo Kang; | emnlp | 2020-11-12 |
| 177 | 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 |
| 178 | AmbigQA: Answering Ambiguous Open-domain Questions IF:2 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 |
| 179 | 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 |
| 180 | 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 |
| 181 | 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 |
| 182 | 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 |
| 183 | Neural Conversational QA: Learning To Reason Vs Exploiting Patterns IF:2 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 |
| 184 | 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 |
| 185 | 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 |
| 186 | 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 |
| 187 | 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 |
| 188 | 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 |
| 189 | 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 |
| 190 | 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 |
| 191 | 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 |
| 192 | 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 |
| 193 | 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 |
| 194 | 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 |
| 195 | Event Extraction By Answering (Almost) Natural Questions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task that extracts the event arguments in an end-to-end manner. |
Xinya Du; Claire Cardie; | emnlp | 2020-11-12 |
| 196 | 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 |
| 197 | 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 |
| 198 | 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 |
| 199 | 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 |
| 200 | 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 |
| 201 | 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 |
| 202 | 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 |
| 203 | HERO: Hierarchical Encoder For Video+Language Omni-representation Pre-training IF:2 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 |
| 204 | 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 |
| 205 | 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 |
| 206 | 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 |
| 207 | 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 |
| 208 | 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 |
| 209 | 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 |
| 210 | 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 |
| 211 | 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 |
| 212 | Compositional And Lexical Semantics In RoBERTa, BERT And DistilBERT: A Case Study On CoQA IF:2 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 |
| 213 | 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 |
| 214 | Video2Commonsense: Generating Commonsense Descriptions To Enrich Video Captioning 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 |
| 215 | Don’t Read Too Much Into It: Adaptive Computation For Open-Domain Question Answering 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 |
| 216 | Multi-hop Inference For Question-driven Summarization 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 |
| 217 | How Do Decisions Emerge Across Layers In Neural Models? Interpretation With Differentiable Masking 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 |
| 218 | Knowledge-guided Open Attribute Value Extraction With Reinforcement Learning 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 |
| 219 | Cross-Thought For Sentence Encoder Pre-training 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 |
| 220 | Learning To Explain: Datasets And Models For Identifying Valid Reasoning Chains In Multihop Question-Answering 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 |
| 221 | Towards Interpreting BERT For Reading Comprehension Based QA 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 |
| 222 | Efficient One-Pass End-to-End Entity Linking For Questions 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 |
| 223 | 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 |
| 224 | Neural Mask Generator: Learning To Generate Adaptive Word Maskings For Language Model Adaptation 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 |
| 225 | MUTANT: A Training Paradigm For Out-of-Distribution Generalization In Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we 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 |
| 226 | Hierarchical Graph Network For Multi-hop Question Answering 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 |
| 227 | EXAMS: A Multi-subject High School Examinations Dataset For Cross-lingual And Multilingual Question Answering 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 |
| 228 | 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 |
| 229 | 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 |
| 230 | 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 |
| 231 | MMFT-BERT: Multimodal Fusion Transformer With BERT Encodings For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present MMFT-BERT(MultiModal FusionTransformer with BERT encodings), to solve Visual Question Answering (VQA) ensuring individual and combined processing of multiple input modalities. |
Aisha Urooj; Amir Mazaheri; Niels Da vitoria lobo; Mubarak Shah; | emnlp | 2020-11-10 |
| 232 | 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 |
| 233 | 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 |
| 234 | 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 |
| 235 | 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 |
| 236 | 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 |
| 237 | 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 |
| 238 | 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 |
| 239 | 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 |
| 240 | 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 |
| 241 | FQuAD: French Question Answering Dataset IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work, we introduce the French Question Answering Dataset (FQuAD). |
Martin d’Hoffschmidt; Wacim Belblidia; Quentin Heinrich; Tom Brendlé; Maxime Vidal; | emnlp | 2020-11-10 |
| 242 | 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 |
| 243 | 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 |
| 244 | INLPSuite: Monolingual Corpora, Evaluation Benchmarks And Pre-trained Multilingual Language Models For Indian Languages IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce NLP resources for 11 major Indian languages from two major language families. |
DIVYANSHU KAKWANI et. al. | emnlp | 2020-11-10 |
| 245 | HybridQA: A Dataset Of Multi-Hop Question Answering Over Tabular And Textual Data IF:2 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 |
| 246 | Improving QA Generalization By Concurrent Modeling Of Multiple Biases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the impact of debiasing methods for improving generalization and propose a general framework for improving the performance on both in-domain and out-of-domain datasets by concurrent modeling of multiple biases in the training data. |
Mingzhu Wu; Nafise Sadat Moosavi; Andreas Rücklé; Iryna Gurevych; | emnlp | 2020-11-10 |
| 247 | Can Pre-training Help VQA With Lexical Variations? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyzed VQA models in the space of paraphrasing. |
Shailza Jolly; Shubham Kapoor; | emnlp | 2020-11-10 |
| 248 | Connecting The Dots: A Knowledgeable Path Generator For Commonsense Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we augment a general commonsense QA framework with a knowledgeable path generator. |
Peifeng Wang; Nanyun Peng; Filip Ilievski; Pedro Szekely; Xiang Ren; | emnlp | 2020-11-10 |
| 249 | 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 |
| 250 | The RELX Dataset And Matching The Multilingual Blanks For Cross-lingual Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For evaluation, we introduce a new public benchmark dataset for cross-lingual relation classification in English, French, German, Spanish, and Turkish, called RELX. |
Abdullatif Köksal; Arzucan Özgür; | emnlp | 2020-11-10 |
| 251 | Towards Zero Shot Conditional Summarization With Adaptive Multi-task Fine-Tuning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we study the problem of conditional summarization in which content selection and surface realization are explicitly conditioned on an ad-hoc natural language question or topic description. |
Travis Goodwin; Max Savery; Dina Demner-Fushman; | emnlp | 2020-11-10 |
| 252 | ConceptBert: Concept-Aware Representation For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a concept-aware algorithm, ConceptBert, for questions which require common sense, or basic factual knowledge from external structured content. |
François Gardères; Maryam Ziaeefard; Baptiste Abeloos; Freddy Lecue; | emnlp | 2020-11-10 |
| 253 | Learning To Model And Ignore Dataset Bias With Mixed Capacity Ensembles IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method that can automatically detect and ignore these kinds of dataset-specific patterns, which we call dataset biases. |
Christopher Clark; Mark Yatskar; Luke Zettlemoyer; | emnlp | 2020-11-10 |
| 254 | Zero-Shot Rationalization By Multi-Task Transfer Learning From Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach that leverages the benefits of both multi-task learning and transfer learning for generating rationales through question answering in a zero-shot fashion. |
Po-Nien Kung; Tse-Hsuan Yang; Yi-Cheng Chen; Sheng-Siang Yin; Yun-Nung Chen; | emnlp | 2020-11-10 |
| 255 | 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 |
| 256 | UNQOVERing Stereotypical Biases Via Underspecified Questions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present UNQOVER, a general framework to probe and quantify biases through underspecified questions. |
Tao Li; Daniel Khashabi; Tushar Khot; Ashish Sabharwal; Vivek Srikumar; | emnlp | 2020-11-10 |
| 257 | Pushing The Limits Of AMR Parsing With Self-Learning 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 |
| 258 | Pragmatic Issue-Sensitive Image Captioning 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 |
| 259 | Natural Language Rationales With Full-Stack Visual Reasoning: From Pixels To Semantic Frames To Commonsense Graphs 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 |
| 260 | DiPair: Fast And Accurate Distillation For Trillion-ScaleText Matching And Pair Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose DiPair – a novel framework for distilling fast and accurate models on text pair tasks. |
JIECAO CHEN et. al. | emnlp | 2020-11-10 |
| 261 | Inexpensive Domain Adaptation Of Pretrained Language Models: Case Studies On Biomedical NER And Covid-19 QA Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a cheaper alternative: We train Word2Vec on target-domain text and align the resulting word vectors with the wordpiece vectors of a general-domain PTLM. |
Nina Poerner; Ulli Waltinger; Hinrich Schütze; | emnlp | 2020-11-10 |
| 262 | Open-Ended Visual Question Answering By Multi-Modal Domain Adaptation 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 |
| 263 | Blockwise Self-Attention For Long Document Understanding 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 |
| 264 | CapWAP: 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 H. Clark; Regina Barzilay; | arxiv-cs.CL | 2020-11-09 |
| 265 | Determining Question-Answer Plausibility In Crowdsourced Datasets Using Multi-Task Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we seek to enable the collection of high-quality question-answer datasets from social media by proposing a novel task for automated quality analysis and data cleaning: question-answer (QA) plausibility. |
Rachel Gardner; Maya Varma; Clare Zhu; Ranjay Krishna; | arxiv-cs.CL | 2020-11-09 |
| 266 | VisBERT: Hidden-State Visualizations For Transformers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We contribute to this challenge by presenting VisBERT, a tool for visualizing the contextual token representations within BERT for the task of (multi-hop) Question Answering. |
Betty van Aken; Benjamin Winter; Alexander Löser; Felix A. Gers; | arxiv-cs.CL | 2020-11-09 |
| 267 | Automated Discovery Of Mathematical Definitions In Text With Deep Neural Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on automatic detection of one-sentence definitions in mathematical texts, which are difficult to separate from surrounding text. We also present a new dataset for definition extraction from mathematical texts. |
Natalia Vanetik; Marina Litvak; Sergey Shevchuk; Lior Reznik; | arxiv-cs.CL | 2020-11-09 |
| 268 | Knowledge-driven Data Construction For Zero-shot Evaluation In Commonsense Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel neuro-symbolic framework for zero-shot question answering across commonsense tasks. |
KAIXIN MA et. al. | arxiv-cs.CL | 2020-11-07 |
| 269 | Language Model Is All You Need: Natural Language Understanding As Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we study the use of a specific family of transfer learning, where the target domain is mapped to the source domain. |
Mahdi Namazifar; Alexandros Papangelis; Gokhan Tur; Dilek Hakkani-Tür; | arxiv-cs.CL | 2020-11-05 |
| 270 | Explain By Evidence: An Explainable Memory-based Neural Network For Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Grounded on that principle, we propose in this paper an explainable, evidence-based memory network architecture, which learns to summarize the dataset and extract supporting evidences to make its decision. |
QUAN TRAN et. al. | arxiv-cs.CL | 2020-11-05 |
| 271 | Improving Commonsense Question Answering By Graph-based Iterative Retrieval Over Multiple Knowledge Sources IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel question-answering method by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and the Cambridge Dictionary, to boost the performance. |
Qianglong Chen; Feng Ji; Haiqing Chen; Yin Zhang; | arxiv-cs.CL | 2020-11-05 |
| 272 | An Improved Attention For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an improved attention-based architecture to solve VQA. |
Tanzila Rahman; Shih-Han Chou; Leonid Sigal; Giuseppe Carenini; | arxiv-cs.CV | 2020-11-04 |
| 273 | Indic-Transformers: An Analysis Of Transformer Language Models For Indian Languages IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to evaluate the performance on Indian languages specifically, we analyze these language models through extensive experiments on multiple downstream tasks in Hindi, Bengali, and Telugu language. |
Kushal Jain; Adwait Deshpande; Kumar Shridhar; Felix Laumann; Ayushman Dash; | arxiv-cs.CL | 2020-11-04 |
| 274 | MK-SQuIT: Synthesizing Questions Using Iterative Template-filling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The aim of this work is to create a framework for synthetically generating question/query pairs with as little human input as possible. We also present an example dataset of 110,000 question/query pairs across four WikiData domains. |
Benjamin A. Spiegel; Vincent Cheong; James E. Kaplan; Anthony Sanchez; | arxiv-cs.CL | 2020-11-04 |
| 275 | CharBERT: Character-aware Pre-trained Language Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a character-aware pre-trained language model named CharBERT improving on the previous methods (such as BERT, RoBERTa) to tackle these problems. |
WENTAO MA et. al. | arxiv-cs.CL | 2020-11-03 |
| 276 | Analyzing Sustainability Reports Using Natural Language Processing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present this tool and the methodology that we used to develop it in the present article. |
Alexandra Luccioni; Emily Baylor; Nicolas Duchene; | arxiv-cs.CL | 2020-11-03 |
| 277 | Constructing A Multi-hop QA Dataset For Comprehensive Evaluation Of Reasoning Steps IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we present a new multi-hop QA dataset, called 2WikiMultiHopQA, which uses structured and unstructured data. |
Xanh Ho; Anh-Khoa Duong Nguyen; Saku Sugawara; Akiko Aizawa; | arxiv-cs.CL | 2020-11-02 |
| 278 | COSMO: Conditional SEQ2SEQ-based Mixture Model For Zero-Shot Commonsense Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Conditional SEQ2SEQ-based Mixture model (COSMO), which provides us with the capabilities of dynamic and diverse content generation. |
Farhad Moghimifar; Lizhen Qu; Yue Zhuo; Mahsa Baktashmotlagh; Gholamreza Haffari; | arxiv-cs.CL | 2020-11-02 |
| 279 | The Devil Is In The Details: Evaluating Limitations Of Transformer-based Methods For Granular Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this expository work, we explore a tangent direction and analyze such models’ performance on tasks that require a more granular level of representation. |
Brihi Joshi; Neil Shah; Francesco Barbieri; Leonardo Neves; | arxiv-cs.CL | 2020-11-02 |
| 280 | Advanced Semantics For Commonsense Knowledge Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a methodology, called Ascent, to automatically build a large-scale knowledge base (KB) of CSK assertions, with advanced expressiveness and both better precision and recall than prior works. |
Tuan-Phong Nguyen; Simon Razniewski; Gerhard Weikum; | arxiv-cs.AI | 2020-11-02 |
| 281 | Improving Conversational Question Answering Systems After Deployment Using Feedback-Weighted Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose feedback-weighted learning based on importance sampling to improve upon an initial supervised system using binary user feedback. |
JON ANDER CAMPOS et. al. | arxiv-cs.CL | 2020-11-01 |
| 282 | Reasoning Over History: Context Aware Visual Dialog IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend the MAC network architecture with Context-aware Attention and Memory (CAM), which attends over control states in past dialog turns to determine the necessary reasoning operations for the current question. |
Muhammad A. Shah; Shikib Mehri; Tejas Srinivasan; | arxiv-cs.CL | 2020-11-01 |
| 283 | Towards Personalized Explanation Of Robotic Planning Via User Feedback IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a system for generating personalized explanations of robotic planning via user feedback. |
Kayla Boggess; Shenghui Chen; Lu Feng; | arxiv-cs.RO | 2020-11-01 |
| 284 | CHIME: Cross-passage Hierarchical Memory Network For Generative Review Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce CHIME, a cross-passage hierarchical memory network for question answering (QA) via text generation. |
Junru Lu; Gabriele Pergola; Lin Gui; Binyang Li; Yulan He; | arxiv-cs.CL | 2020-11-01 |
| 285 | A Sui Generis QA Approach Using RoBERTa For Adverse Drug Event Identification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a question answering framework that exploits the robustness, masking and dynamic attention capabilities of RoBERTa by a technique of domain adaptation and attempt to overcome the aforementioned limitations. |
Harshit Jain; Nishant Raj; Suyash Mishra; | arxiv-cs.CL | 2020-10-30 |
| 286 | A New Neural Search And Insights Platform For Navigating And Organizing AI Research IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To provide AI researchers with modern tools for dealing with the explosive growth of the research literature in their field, we introduce a new platform, AI Research Navigator, that combines classical keyword search with neural retrieval to discover and organize relevant literature. |
MARZIEH FADAEE et. al. | arxiv-cs.CL | 2020-10-30 |
| 287 | Leveraging Extracted Model Adversaries For Improved Black Box Attacks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a method for adversarial input generation against black box models for reading comprehension based question answering. |
Naveen Jafer Nizar; Ari Kobren; | arxiv-cs.LG | 2020-10-30 |
| 288 | VECO: Variable Encoder-decoder Pre-training For Cross-lingual Understanding And Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, this paper presents a variable encoder-decoder (VECO) pre-training approach to unify the two mainstreams in both model architectures and pre-training tasks. |
FULI LUO et. al. | arxiv-cs.CL | 2020-10-29 |
| 289 | Loss-rescaling VQA: Revisiting Language Prior Problem From A Class-imbalance View IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to interpret the language prior problem in VQA from a class-imbalance view. |
Yangyang Guo; Liqiang Nie; Zhiyong Cheng; Qi Tian; | arxiv-cs.CV | 2020-10-29 |
| 290 | CliniQG4QA: Generating Diverse Questions For Domain Adaptation Of Clinical Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose a simple yet effective framework, CliniQG4QA, which leverages question generation (QG) to synthesize QA pairs on new clinical contexts and boosts QA models without requiring manual annotations. |
Xiang Yue; Xinliang Frederick Zhang; Ziyu Yao; Simon Lin; Huan Sun; | arxiv-cs.CL | 2020-10-29 |
| 291 | Leveraging Visual Question Answering To Improve Text-to-Image Synthesis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an effective way to combine Text-to-Image (T2I) synthesis with Visual Question Answering (VQA) to improve the image quality and image-text alignment of generated images by leveraging the VQA 2.0 dataset. |
Stanislav Frolov; Shailza Jolly; Jörn Hees; Andreas Dengel; | arxiv-cs.CV | 2020-10-28 |
| 292 | Flexible Retrieval With NMSLIB And FlexNeuART IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our objective is to introduce to the NLP community an existing k-NN search library NMSLIB, a new retrieval toolkit FlexNeuART, as well as their integration capabilities. |
Leonid Boytsov; Eric Nyberg; | arxiv-cs.IR | 2020-10-28 |
| 293 | Effective FAQ Retrieval And Question Matching With Unsupervised Knowledge Injection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend this line of research by combining the clues gathered from the q-Q similarity measure and the q-A relevance measure and meanwhile injecting extra word interaction information, distilled from a generic (open domain) knowledge base, into a contextual language model for inferring the q-A relevance. |
Wen-Ting Tseng; Tien-Hong Lo; Yung-Chang Hsu; Berlin Chen; | arxiv-cs.AI | 2020-10-27 |
| 294 | Co-attentional Transformers For Story-Based Video Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel co-attentional transformer model to better capture long-term dependencies seen in visual stories such as dramas and measure its performance on the video question answering task. |
Björn Bebensee; Byoung-Tak Zhang; | arxiv-cs.CV | 2020-10-27 |
| 295 | MMFT-BERT: Multimodal Fusion Transformer With BERT Encodings For Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present MMFT-BERT(MultiModal Fusion Transformer with BERT encodings), to solve Visual Question Answering (VQA) ensuring individual and combined processing of multiple input modalities. |
Aisha Urooj Khan; Amir Mazaheri; Niels da Vitoria Lobo; Mubarak Shah; | arxiv-cs.CV | 2020-10-27 |
| 296 | How We Refactor And How We Document It? On The Use Of Supervised Machine Learning Algorithms To Classify Refactoring Documentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To cope with the above-mentioned limitations, we aim to better understand what motivates developers to apply refactoring by mining and classifying a large set of 111,884 commits containing refactorings, extracted from 800 Java projects. |
EMAN ABDULLAH ALOMAR et. al. | arxiv-cs.SE | 2020-10-26 |
| 297 | ExplanationLP: Abductive Reasoning For Explainable Science Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel approach for answering and explaining multiple-choice science questions by reasoning on grounding and abstract inference chains. |
Mokanarangan Thayaparan; Marco Valentino; André Freitas; | arxiv-cs.AI | 2020-10-25 |
| 298 | Learning to Deceive Knowledge Graph Augmented Models Via Targeted Perturbation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we question whether these models are really behaving as we expect. |
MRIGANK RAMAN et. al. | arxiv-cs.CL | 2020-10-24 |
| 299 | Learning Contextualized Knowledge Structures For Commonsense Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose Hybrid Graph Network (HGN), a neural-symbolic model that reasons over both extracted (human-labeled) and generated facts within the same learned graph structure. |
JUN YAN et. al. | arxiv-cs.CL | 2020-10-24 |
| 300 | ReadOnce Transformers: Reusable Representations Of Text For Transformers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a transformer-based approach, ReadOnce Transformers, that is trained to build such information-capturing representations of text. |
Shih-Ting Lin; Ashish Sabharwal; Tushar Khot; | arxiv-cs.CL | 2020-10-24 |
| 301 | Beyond VQA: Generating Multi-word Answer And Rationale To Visual Questions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a completely generative formulation where a multi-word answer is generated for a visual query. |
Radhika Dua; Sai Srinivas Kancheti; Vineeth N Balasubramanian; | arxiv-cs.CV | 2020-10-24 |
| 302 | Efficient End-to-end Learning Of Cross-event Dependencies For Document-level Event Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an end-to-end model leveraging Deep Value Networks (DVN), a structured prediction algorithm, to efficiently capture cross-event dependencies for document-level event extraction. |
Kung-Hsiang Huang; Nanyun Peng; | arxiv-cs.CL | 2020-10-24 |
| 303 | RUArt: A Novel Text-Centered Solution For Text-Based Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel text-centered method called RUArt (Reading, Understanding and Answering the Related Text) for text-based VQA. |
ZAN-XIA JIN et. al. | arxiv-cs.CV | 2020-10-24 |
| 304 | AQuaMuSe: Automatically Generating Datasets For Query-Based Multi-Document Summarization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a scalable approach called AQuaMuSe to automatically mine qMDS examples from question answering datasets and large document corpora. |
Sayali Kulkarni; Sheide Chammas; Wan Zhu; Fei Sha; Eugene Ie; | arxiv-cs.CL | 2020-10-23 |
| 305 | Large Scale Knowledge Graph Based Synthetic Corpus Generation For Knowledge-Enhanced Language Model Pre-training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we verbalize the entire Wikidata KG, and create a KG-Text aligned corpus in the training process. |
Oshin Agarwal; Heming Ge; Siamak Shakeri; Rami Al-Rfou; | arxiv-cs.CL | 2020-10-23 |
| 306 | Unsupervised Multi-hop Question Answering By Question Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose the problem of \textit{unsupervised} multi-hop QA, assuming that no human-labeled multi-hop question-answer pairs are available. |
Liangming Pan; Wenhu Chen; Wenhan Xiong; Min-Yen Kan; William Yang Wang; | arxiv-cs.CL | 2020-10-23 |
| 307 | Retrieve, Rerank, Read, Then Iterate: Answering Open-Domain Questions Of Arbitrary Complexity From Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we propose a unified system to answer open-domain questions of arbitrary complexity directly from text that works with off-the-shelf retrieval systems on arbitrary text collections. To emulate a more realistic setting, we also constructed a new unified benchmark by collecting about 200 multi-hop questions that require three Wikipedia pages to answer, and combining them with existing datasets. |
Peng Qi; Haejun Lee; Oghenetegiri TG Sido; Christopher D. Manning; | arxiv-cs.CL | 2020-10-23 |
| 308 | Neural Passage Retrieval With Improved Negative Contrast IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we explore the effects of negative sampling in dual encoder models used to retrieve passages for automatic question answering. |
Jing Lu; Gustavo Hernandez Abrego; Ji Ma; Jianmo Ni; Yinfei Yang; | arxiv-cs.CL | 2020-10-23 |
| 309 | Synthetic Data Augmentation For Zero-Shot Cross-Lingual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method to improve the Cross-lingual Question Answering performance without requiring additional annotated data, leveraging Question Generation models to produce synthetic samples in a cross-lingual fashion. |
ARIJ RIABI et. al. | arxiv-cs.CL | 2020-10-23 |
| 310 | XOR QA: Cross-lingual Open-Retrieval Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this dataset, we introduce three new tasks that involve cross-lingual document retrieval using multi-lingual and English resources. We construct a large-scale dataset built on questions from TyDi QA lacking same-language answers. |
AKARI ASAI et. al. | arxiv-cs.CL | 2020-10-22 |
| 311 | EIGEN: Event Influence GENeration Using Pre-trained Language Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present EIGEN – a method to leverage pre-trained language models to generate event influences conditioned on a context, nature of their influence, and the distance in a reasoning chain. |
AMAN MADAAN et. al. | arxiv-cs.CL | 2020-10-22 |
| 312 | Summarizing Utterances From Japanese Assembly Minutes Using Political Sentence-BERT-based Method For QA Lab-PoliInfo-2 Task Of NTCIR-15 IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes our approach to solving the task and discusses its results. |
Daiki Shirafuji; Hiromichi Kameya; Rafal Rzepka; Kenji Araki; | arxiv-cs.CL | 2020-10-22 |
| 313 | Multilingual Synthetic Question And Answer Generation For Cross-Lingual Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple method to generate large amounts of multilingual question and answer pairs by a single generative model. |
Siamak Shakeri; Noah Constant; Mihir Sanjay Kale; Linting Xue; | arxiv-cs.CL | 2020-10-22 |
| 314 | Challenges In Information Seeking QA:Unanswerable Questions And Paragraph Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze two such datasets (Natural Questions and TyDi QA) to identify remaining headrooms: paragraph selection and answerability classification, i.e. determining whether the paired evidence document contains the answer to the query or not. |
Akari Asai; Eunsol Choi; | arxiv-cs.CL | 2020-10-22 |
| 315 | Knowledge Distillation For Improved Accuracy In Spoken Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the issue, we present a novel distillation framework. |
Chenyu You; Nuo Chen; Yuexian Zou; | arxiv-cs.CL | 2020-10-21 |
| 316 | Contextualized Attention-based Knowledge Transfer For Spoken Conversational Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the problem, we propose CADNet, a novel contextualized attention-based distillation approach, which applies both cross-attention and self-attention to obtain ASR-robust contextualized embedding representations of the passage and dialogue history for performance improvements. |
Chenyu You; Nuo Chen; Yuexian Zou; | arxiv-cs.CL | 2020-10-21 |
| 317 | Is Retriever Merely An Approximator Of Reader? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Experimental results show that our method can enhance the document recall rate as well as the end-to-end QA accuracy of off-the-shelf retrievers in open-domain QA tasks. |
Sohee Yang; Minjoon Seo; | arxiv-cs.CL | 2020-10-21 |
| 318 | Exploring Sequence-to-Sequence Models For SPARQL Pattern Composition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this short paper, we explore the use of architectures based on Neural Machine Translation called Neural SPARQL Machines to learn pattern compositions. |
Anand Panchbhai; Tommaso Soru; Edgard Marx; | arxiv-cs.CL | 2020-10-21 |
| 319 | RECONSIDER: Re-Ranking Using Span-Focused Cross-Attention For Open Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a simple and effective re-ranking approach (RECONSIDER) for span-extraction tasks, that improves upon the performance of large pre-trained MRC models. |
Srinivasan Iyer; Sewon Min; Yashar Mehdad; Wen-tau Yih; | arxiv-cs.CL | 2020-10-21 |
| 320 | Unsupervised Deep Learning Based Multiple Choices Question Answering: Start Learning From Basic Knowledge IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the possibility of almost unsupervised Multiple Choices Question Answering (MCQA). |
Chi-Liang Liu; Hung-yi Lee; | arxiv-cs.CL | 2020-10-21 |
| 321 | Kwame: A Bilingual AI Teaching Assistant For Online SuaCode Courses IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Given the multilingual context of our students (learners across 38 African countries), in this work, we developed an AI Teaching Assistant (Kwame) that provides answers to students’ coding questions from our SuaCode courses in English and French. |
George Boateng; | arxiv-cs.CL | 2020-10-21 |
| 322 | Open Question Answering Over Tables And Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Most questions in OTT-QA require multi-hop inference across tabular data and unstructured text, and the evidence required to answer a question can be distributed in different ways over these two types of input, making evidence retrieval challenging—our baseline model using an iterative retriever and BERT-based reader achieves an exact match score less than 10%. |
Wenhu Chen; Ming-Wei Chang; Eva Schlinger; William Wang; William W. Cohen; | arxiv-cs.CL | 2020-10-20 |
| 323 | SOrT-ing VQA Models : Contrastive Gradient Learning For Improved Consistency IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recent research in Visual Question Answering (VQA) has revealed state-of-the-art models to be inconsistent in their understanding of the world — they answer seemingly difficult questions requiring reasoning correctly but get simpler associated sub-questions wrong. |
Sameer Dharur; Purva Tendulkar; Dhruv Batra; Devi Parikh; Ramprasaath R. Selvaraju; | arxiv-cs.CV | 2020-10-20 |
| 324 | 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. | arxiv-cs.CL | 2020-10-20 |
| 325 | 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 propose 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 F. Chen; Steven C. H. Hoi; | arxiv-cs.CV | 2020-10-20 |
| 326 | Bi-directional Cognitive Thinking Network For Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory. |
WEI PENG et. al. | arxiv-cs.CL | 2020-10-20 |
| 327 | Extracting Procedural Knowledge From Technical Documents IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we cover some of this ground by — 1) Providing insights on how structural and linguistic properties of documents can be grouped to define types of procedures, 2) Analyzing documents to extract the relevant linguistic and structural properties, and 3) Formulating procedure identification as a classification problem that leverages the features of the document derived from the above analysis. |
Shivali Agarwal; Shubham Atreja; Vikas Agarwal; | arxiv-cs.AI | 2020-10-20 |
| 328 | Better Distractions: Transformer-based Distractor Generation And Multiple Choice Question Filtering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we train a GPT-2 language model to generate three distractors for a given question and text context, using the RACE dataset. |
Jeroen Offerijns; Suzan Verberne; Tessa Verhoef; | arxiv-cs.CL | 2020-10-19 |
| 329 | Event-QA: A Dataset For Event-Centric Question Answering Over Knowledge Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the Event-QA dataset for answering event-centric questions over knowledge graphs. |
Tarcísio Souza Costa; Simon Gottschalk; Elena Demidova; | cikm | 2020-10-19 |
| 330 | Hierarchical Query Graph Generation For Complex Question Answering Over Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a Director-Actor-Critic framework to overcome these challenges. |
YUNQI QIU et. al. | cikm | 2020-10-19 |
| 331 | AliMeKG: Domain Knowledge Graph Construction And Application In E-commerce IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the paper, we systematically introduce how we construct domain knowledge graph from free text, and demonstrate its business value with several applications. |
FENG-LIN LI et. al. | cikm | 2020-10-19 |
| 332 | Question Generation For Supporting Informational Query Intents IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to generate self-explanatory questions that focus on the main document topics and are answerable with variable length passages as appropriate. |
Xusen Yin; Jonathan May; Li Zhou; Kevin Small; | arxiv-cs.CL | 2020-10-19 |
| 333 | Offline Evaluation By Maximum Similarity To An Ideal Ranking IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Rather than propose extensions to these measures, we instead propose a radical simplification to replace them. |
Charles L. A. Clarke; Mark D. Smucker; Alexandra Vtyurina; | cikm | 2020-10-19 |
| 334 | Learning To Generate Reformulation Actions For Scalable Conversational Query Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For action generation, we propose a multi-task learning framework enhanced by coreference resolution, and introduce grammar constraints into the decoding process. |
ZIHAN XU et. al. | cikm | 2020-10-19 |
| 335 | Fine-Grained Relevance Annotations For Multi-Task Document Ranking And Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present FiRA: a novel dataset of Fine-Grained Relevance Annotations. |
Sebastian Hofstätter; Markus Zlabinger; Mete Sertkan; Michael Schröder; Allan Hanbury; | cikm | 2020-10-19 |
| 336 | Neural Relation Extraction On Wikipedia Tables For Augmenting Knowledge Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We help close this gap with a neural method that uses contextual information surrounding a table in a Wikipedia article to extract relations between entities appearing in the same row of a table or between the entity of said article and entities appearing in the table. |
Erin Macdonald; Denilson Barbosa; | cikm | 2020-10-19 |
| 337 | Continual Domain Adaptation For Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the CDA task, we propose several BERT-based continual learning MRC models using either regularization-based methodology or dynamic-architecture paradigm. |
LIXIN SU et. al. | cikm | 2020-10-19 |
| 338 | Technical Question Answering Across Tasks And Domains IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains. |
WENHAO YU et. al. | arxiv-cs.CL | 2020-10-19 |
| 339 | CauseNet: Towards A Causality Graph Extracted From The Web IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Notwithstanding this challenge, we compile CauseNet, a large-scale knowledge base of claimed causal relations between causal concepts. |
Stefan Heindorf; Yan Scholten; Henning Wachsmuth; Axel-Cyrille Ngonga Ngomo; Martin Potthast; | cikm | 2020-10-19 |
| 340 | Opinion-aware Answer Generation For Review-driven Question Answering In E-Commerce IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we tackle opinion-aware answer generation by jointly learning answer generation and opinion mining tasks with a unified model. |
Yang Deng; Wenxuan Zhang; Wai Lam; | cikm | 2020-10-19 |
| 341 | Knowledge Graph-based Question Answering With Electronic Health Records IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We hypothesize that the graph-based approach is more suitable for EHR QA as graphs can represent relations between entities and values more naturally compared to tables, which essentially require JOIN operations. |
Junwoo Park; Youngwoo Cho; Haneol Lee; Jaegul Choo; Edward Choi; | arxiv-cs.DB | 2020-10-19 |
| 342 | The RELX Dataset And Matching The Multilingual Blanks For Cross-Lingual Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this issue, we propose two cross-lingual relation classification models: a baseline model based on Multilingual BERT and a new multilingual pretraining setup, which significantly improves the baseline with distant supervision. For evaluation, we introduce a new public benchmark dataset for cross-lingual relation classification in English, French, German, Spanish, and Turkish, called RELX. We also provide the RELX-Distant dataset, which includes hundreds of thousands of sentences with relations from Wikipedia and Wikidata collected by distant supervision for these languages. |
Abdullatif Köksal; Arzucan Özgür; | arxiv-cs.CL | 2020-10-19 |
| 343 | Do People And Neural Nets Pay Attention To The Same Words: Studying Eye-tracking Data For Non-factoid QA Evaluation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Similarity was found, consequently, we propose a method to exploit the BERT attention map to generate suggestions that simulate eye gaze during user evaluation. |
VALERIA BOLOTOVA et. al. | cikm | 2020-10-19 |
| 344 | Feature Extraction For Large-Scale Text Collections IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Fxt, an open-source framework to perform efficient and scalable feature extraction. |
Luke Gallagher; Antonio Mallia; J. Shane Culpepper; Torsten Suel; B. Barla Cambazoglu; | cikm | 2020-10-19 |
| 345 | Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder For Long-Form Document Matching IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the issue by proposing the Siamese Multi-depth Transformer-based Hierarchical (SMITH) Encoder for long-form document matching. |
Liu Yang; Mingyang Zhang; Cheng Li; Michael Bendersky; Marc Najork; | cikm | 2020-10-19 |
| 346 | BERTnesia: Investigating The Capture And Forgetting Of Knowledge In BERT IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we probe BERT specifically to understand and measure the relational knowledge it captures. |
Jonas Wallat; Jaspreet Singh; Avishek Anand; | arxiv-cs.CL | 2020-10-19 |
| 347 | Understanding Unnatural Questions Improves Reasoning Over Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated questions which are more convenient to parse. |
Xiao-Yu Guo; Yuan-Fang Li; Gholamreza Haffari; | arxiv-cs.CL | 2020-10-19 |
| 348 | Ranking Clarification Questions Via Natural Language Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For the task of ranking clarification questions, we hypothesize that determining whether a clarification question pertains to a missing entry in a given post (on QA forums such as StackExchange) could be considered as a special case of Natural Language Inference (NLI), where both the post and the most relevant clarification question point to a shared latent piece of information or context. |
Vaibhav Kumar; Vikas Raunak; Jamie Callan; | cikm | 2020-10-19 |
| 349 | Schema2QA: High-Quality And Low-Cost Q&A Agents For The Structured Web Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes Schema2QA, an open-source toolkit that can generate a Q&A system from a database schema augmented with a few annotations for each field. |
Silei Xu; Giovanni Campagna; Jian Li; Monica S. Lam; | cikm | 2020-10-19 |
| 350 | Towards Data Distillation For End-to-end Spoken Conversational Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, instead of adopting automatically generated speech transcripts with highly noisy data, we propose a novel unified data distillation approach, DDNet, which directly fuse audio-text features to reduce the misalignment between automatic speech recognition hypotheses and the reference transcriptions. |
Chenyu You; Nuo Chen; Fenglin Liu; Dongchao Yang; Yuexian Zou; | arxiv-cs.CL | 2020-10-18 |
| 351 | Hierarchical Conditional Relation Networks For Multimodal Video Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For (a) this paper introduces a general-reusable neural unit dubbed Conditional Relation Network (CRN) taking as input a set of tensorial objects and translating into a new set of objects that encode relations of the inputs. |
Thao Minh Le; Vuong Le; Svetha Venkatesh; Truyen Tran; | arxiv-cs.CV | 2020-10-17 |
| 352 | Question Answering Over Knowledge Base Using Language Model Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focused on using a pre-trained language model for the Knowledge Base Question Answering task. |
Sai Sharath Japa; Rekabdar Banafsheh; | arxiv-cs.CL | 2020-10-17 |
| 353 | New Ideas And Trends In Deep Multimodal Content Understanding: A Review IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unlike classic reviews of deep learning where monomodal image classifiers such as VGG, ResNet and Inception module are central topics, this paper will examine recent multimodal deep models and structures, including auto-encoders, generative adversarial nets and their variants. |
Wei Chen; Weiping Wang; Li Liu; Michael S. Lew; | arxiv-cs.CV | 2020-10-16 |
| 354 | Answer-checking In Context: A Multi-modal FullyAttention Network For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we mimic this process and propose a fully attention based VQA architecture. |
Hantao Huang; Tao Han; Wei Han; Deep Yap; Cheng-Ming Chiang; | arxiv-cs.CV | 2020-10-16 |
| 355 | QA2Explanation: Generating And Evaluating Explanations For Question Answering Systems Over Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, in this paper, we develop an automatic approach for generating explanations during various stages of a pipeline-based QA system. |
Saeedeh Shekarpour; Abhishek Nadgeri; Kuldeep Singh; | arxiv-cs.CL | 2020-10-16 |
| 356 | Delaying Interaction Layers In Transformer-based Encoders For Efficient Open Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a more direct and complementary solution which consists in applying a generic change in the architecture of transformer-based models to delay the attention between subparts of the input and allow a more efficient management of computations. |
Wissam Siblini; Mohamed Challal; Charlotte Pasqual; | arxiv-cs.CL | 2020-10-16 |
| 357 | RocketQA: An Optimized Training Approach To Dense Passage Retrieval For Open-Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. |
YINGQI QU YUCHEN DING et. al. | arxiv-cs.CL | 2020-10-16 |
| 358 | Length-Adaptive Transformer: Train Once With Length Drop, Use Anytime With Search IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend PoWER-BERT to address this issue of inefficiency and redundancy. |
Gyuwan Kim; Kyunghyun Cho; | arxiv-cs.CL | 2020-10-14 |
| 359 | A Graph Representation Of Semi-structured Data For Web Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. |
XINGYAO ZHANG et. al. | arxiv-cs.CL | 2020-10-14 |
| 360 | Finding Minimum Connected Subgraphs With Ontology Exploration On Large RDF Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the following problem: given a knowledge graph (KG) and a set of input vertices (representing concepts or entities) and edge labels, we aim to find the smallest connected subgraphs containing all of the inputs. |
Xiangnan Ren; Neha Sengupta; Xuguang Ren; Junhu Wang; Olivier Curé; | arxiv-cs.DB | 2020-10-13 |
| 361 | CoRel: Seed-Guided Topical Taxonomy Construction By Concept Learning And Relation Transferring Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method for seed-guided topical taxonomy construction, which takes a corpus and a seed taxonomy described by concept names as input, and constructs a more complete taxonomy based on user’s interest, wherein each node is represented by a cluster of coherent terms. |
Jiaxin Huang; Yiqing Xie; Yu Meng; Yunyi Zhang; Jiawei Han; | arxiv-cs.CL | 2020-10-13 |
| 362 | CM-BERT: Cross-Modal BERT For Text-Audio Sentiment Analysis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Cross-Modal BERT (CM-BERT), which relies on the interaction of text and audio modality to fine-tune the pre-trained BERT model. |
Kaicheng Yang; Hua Xu; Kai Gao; | mm | 2020-10-12 |
| 363 | Medical Visual Question Answering Via Conditional Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel conditional reasoning framework for Med-VQA, aiming to automatically learn effective reasoning skills for various Med-VQA tasks. |
Li-Ming Zhan; Bo Liu; Lu Fan; Jiaxin Chen; Xiao-Ming Wu; | mm | 2020-10-12 |
| 364 | Memory-Based Network For Scene Graph With Unbalanced Relations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For these reasons, we propose a novel scene graph generation model that can effectively improve the detection of low-frequency relations. |
WEITAO WANG et. al. | mm | 2020-10-12 |
| 365 | 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. | arxiv-cs.CL | 2020-10-12 |
| 366 | Multi-modal Multi-relational Feature Aggregation Network For Medical Knowledge Representation Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Multi-modal Multi-Relational Feature Aggregation Network (MMRFAN) for medical knowledge representation learning. |
Yingying Zhang; Quan Fang; Shengsheng Qian; Changsheng Xu; | mm | 2020-10-12 |
| 367 | Counterfactual Variable Control For Robust And Interpretable Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we inspect such spurious capability of QA models using causal inference. |
Sicheng Yu; Yulei Niu; Shuohang Wang; Jing Jiang; Qianru Sun; | arxiv-cs.CL | 2020-10-12 |
| 368 | DeVLBert: Learning Deconfounded Visio-Linguistic Representations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned. |
SHENGYU ZHANG et. al. | mm | 2020-10-12 |
| 369 | Multi-modal Attentive Graph Pooling Model For Community Question Answer Matching IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a multi-modal attentive graph pooling approach (MMAGP) to model the multi-modal content of questions and answers with GNNs in a unified framework, which explores the multi-modal and redundant properties of CQA systems. |
Jun Hu; Quan Fang; Shengsheng Qian; Changsheng Xu; | mm | 2020-10-12 |
| 370 | Boosting Visual Question Answering With Context-aware Knowledge Aggregation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the challenging issue, we propose a Knowledge Graph Augmented (KG-Aug) model which conducts context-aware knowledge aggregation on external knowledge graphs, requiring no ground-truth knowledge facts for extra supervision. |
Guohao Li; Xin Wang; Wenwu Zhu; | mm | 2020-10-12 |
| 371 | Exploring Language Prior For Mode-Sensitive Visual Attention Modeling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new probabilistic framework for attention, and introduce the concept ofmode to model the flexibility and adaptability of attention modulation in complex environments. |
XIAOSHUAI SUN et. al. | mm | 2020-10-12 |
| 372 | Dual Hierarchical Temporal Convolutional Network With QA-Aware Dynamic Normalization For Video Story Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework named Dual Hierarchical Temporal Convolutional Network (DHTCN) to address the aforementioned defects together. |
Fei Liu; Jing Liu; Xinxin Zhu; Richang Hong; Hanqing Lu; | mm | 2020-10-12 |
| 373 | Contrast And Classify: Alternate Training For Robust VQA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel training paradigm (ConCAT) that alternately optimizes cross-entropy and contrastive losses. |
Yash Kant; Abhinav Moudgil; Dhruv Batra; Devi Parikh; Harsh Agrawal; | arxiv-cs.CV | 2020-10-12 |
| 374 | Neural-Symbolic Reasoning On Knowledge Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this survey, we take a thorough look at the development of the symbolic reasoning, neural reasoning and the neural-symbolic reasoning on knowledge graphs. |
Jing Zhang; Bo Chen; Lingxi Zhang; Xirui Ke; Haipeng Ding; | arxiv-cs.AI | 2020-10-12 |
| 375 | Cascade Reasoning Network For Text-based Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of text-based visual question answering (T-VQA) in this paper. |
FEN LIU et. al. | mm | 2020-10-12 |
| 376 | Photo Stream Question Answer IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new visual question answering (VQA) task — Photo Stream QA, which aims to answer the open-ended questions about a narrative photo stream. |
WENQIAO ZHANG et. al. | mm | 2020-10-12 |
| 377 | Learning Self-Supervised Multimodal Representations Of Human Behaviour IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this extended abstract, I present the direction of research that I have followed during the first half of my PhD, along with ideas and work in progress for the second half. |
Abhinav Shukla; | mm | 2020-10-12 |
| 378 | K-armed Bandit Based Multi-Modal Network Architecture Search For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a cross-modal network architecture search (NAS) algorithm for VQA, termed as k-Armed Bandit based NAS (KAB-NAS). |
YIYI ZHOU et. al. | mm | 2020-10-12 |
| 379 | Deep Multimodal Neural Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we devise a generalized deep multimodal neural architecture search (MMnas) framework for various multimodal learning tasks. |
ZHOU YU et. al. | mm | 2020-10-12 |
| 380 | Towards Accurate And Reliable Energy Measurement Of NLP Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that existing software-based energy measurements are not accurate because they do not take into account hardware differences and how resource utilization affects energy consumption. We release the code and data at https://github.com/csarron/sustainlp2020-energy. |
Qingqing Cao; Aruna Balasubramanian; Niranjan Balasubramanian; | arxiv-cs.CL | 2020-10-11 |
| 381 | Open-Domain Question Answering Goes Conversational Via Question Rewriting IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 81K question-answer pairs. |
RAVITEJA ANANTHA et. al. | arxiv-cs.IR | 2020-10-10 |
| 382 | 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 J. Semnani; Silei Xu; Monica S. Lam; | arxiv-cs.CL | 2020-10-10 |
| 383 | Interpretable Neural Computation For Real-World Compositional Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We aim to combine the two to build an interpretable framework for real-world compositional VQA. |
Ruixue Tang; Chao Ma; | arxiv-cs.CV | 2020-10-10 |
| 384 | Relation Extraction As Two-way Span-Prediction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. |
Amir DN Cohen; Shachar Rosenman; Yoav Goldberg; | arxiv-cs.CL | 2020-10-09 |
| 385 | 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 J. Semnani; Giovanni Campagna; Monica S. Lam; | arxiv-cs.CL | 2020-10-09 |
| 386 | Artificial Intelligence (AI) In Action: Addressing The COVID-19 Pandemic With Natural Language Processing (NLP) IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We detail work on four core NLP tasks: information retrieval, named entity recognition, literature-based discovery, and question answering. |
QINGYU CHEN et. al. | arxiv-cs.CL | 2020-10-09 |
| 387 | 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; | arxiv-cs.CL | 2020-10-08 |
| 388 | Improving QA Generalization By Concurrent Modeling Of Multiple Biases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the impact of debiasing methods for improving generalization and propose a general framework for improving the performance on both in-domain and out-of-domain datasets by concurrent modeling of multiple biases in the training data. |
Mingzhu Wu; Nafise Sadat Moosavi; Andreas Rücklé; Iryna Gurevych; | arxiv-cs.CL | 2020-10-07 |
| 389 | Unsupervised Evaluation For Question Answering With Transformers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we begin by investigating the hidden representations of questions, answers, and contexts in transformer-based QA architectures. |
Lukas Muttenthaler; Isabelle Augenstein; Johannes Bjerva; | arxiv-cs.CL | 2020-10-07 |
| 390 | SRLGRN: Semantic Role Labeling Graph Reasoning Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a graph reasoning network based on the semantic structure of the sentences to learn cross paragraph reasoning paths and find the supporting facts and the answer jointly. |
Chen Zheng; Parisa Kordjamshidi; | arxiv-cs.CL | 2020-10-07 |
| 391 | Vision Skills Needed To Answer Visual Questions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our first aim is to identify the common vision skills needed for both scenarios. |
Xiaoyu Zeng; Yanan Wang; Tai-Yin Chiu; Nilavra Bhattacharya; Danna Gurari; | arxiv-cs.HC | 2020-10-07 |
| 392 | 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. | arxiv-cs.CL | 2020-10-07 |
| 393 | Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this finding, we propose a cross-architecture training procedure with a margin focused loss (Margin-MSE), that adapts knowledge distillation to the varying score output distributions of different BERT and non-BERT passage ranking architectures. |
Sebastian Hofstätter; Sophia Althammer; Michael Schröder; Mete Sertkan; Allan Hanbury; | arxiv-cs.IR | 2020-10-06 |
| 394 | Context Modeling With Evidence Filter For Multiple Choice Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the challenge, we propose a simple yet effective approach termed evidence filtering to model the relationships between the encoded contexts with respect to different options collectively and to potentially highlight the evidence sentences and filter out unrelated sentences. |
Sicheng Yu; Hao Zhang; Wei Jing; Jing Jiang; | arxiv-cs.CL | 2020-10-06 |
| 395 | DaNetQA: A Yes/no Question Answering Dataset For The Russian Language IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a reproducible approach to DaNetQA creation and investigate transfer learning methods for task and language transferring. |
TAISIA GLUSHKOVA et. al. | arxiv-cs.CL | 2020-10-06 |
| 396 | Joint Semantics And Data-Driven Path Representation For Knowledge Graph Inference IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the above challenges, in this work, we propose a novel joint semantics and data-driven path representation that balances explainability and generalization in the framework of KG embedding. |
GUANGLIN NIU et. al. | arxiv-cs.AI | 2020-10-06 |
| 397 | DiPair: Fast And Accurate Distillation For Trillion-Scale Text Matching And Pair Modeling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose DiPair — a novel framework for distilling fast and accurate models on text pair tasks. |
JIECAO CHEN et. al. | arxiv-cs.CL | 2020-10-06 |
| 398 | Finding The Evidence: Localization-aware Answer Prediction For Text Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As such, this paper proposes a localization-aware answer prediction network (LaAP-Net) to address this challenge. |
Wei Han; Hantao Huang; Tao Han; | arxiv-cs.CV | 2020-10-06 |
| 399 | 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 Uddin Ahmad; Jianfeng Chi; Yuan Tian; Kai-Wei Chang; | arxiv-cs.CL | 2020-10-06 |
| 400 | 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; Barnabás Póczos; Jaime Carbonell; | arxiv-cs.CL | 2020-10-06 |
| 401 | BERT Knows Punta Cana Is Not Just Beautiful, It’s Gorgeous: Ranking Scalar Adjectives With Contextualised Representations 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; | arxiv-cs.CL | 2020-10-06 |
| 402 | QADiscourse — Discourse Relations As QA Pairs: Representation, Crowdsourcing And Baselines 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. Based on our proposed representation, we collect a novel and wide-coverage QADiscourse dataset, and present baseline algorithms for predicting QADiscourse relations. |
Valentina Pyatkin; Ayal Klein; Reut Tsarfaty; Ido Dagan; | arxiv-cs.CL | 2020-10-06 |
| 403 | UnQovering Stereotyping Biases Via Underspecified Questions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present UNQOVER, a general framework to probe and quantify biases through underspecified questions. |
Tao Li; Tushar Khot; Daniel Khashabi; Ashish Sabharwal; Vivek Srikumar; | arxiv-cs.CL | 2020-10-05 |
| 404 | When In Doubt, Ask: Generating Answerable And Unanswerable Questions, Unsupervised IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A state-of-the-art model based on deep transformers is used to inspect the impact of using synthetic answerable and unanswerable questions to complement a well-known human-made dataset. |
Liubov Nikolenko; Pouya Rezazadeh Kalehbasti; | arxiv-cs.CL | 2020-10-04 |
| 405 | Attention Guided Semantic Relationship Parsing For Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a general purpose semantic relationship parser which generates a semantic feature vector for each subject-predicate-object triplet in an image, and a Mutual and Self Attention (MSA) mechanism that learns to identify relationship triplets that are important to answer the given question. |
Moshiur Farazi; Salman Khan; Nick Barnes; | arxiv-cs.CV | 2020-10-04 |
| 406 | Reading Comprehension As Natural Language Inference: A Semantic Analysis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we explore the utility of NLI for one of the most prominent downstream tasks, viz. |
ANSHUMAN MISHRA et. al. | arxiv-cs.CL | 2020-10-04 |
| 407 | CAPTION: Correction By Analyses, POS-Tagging And Interpretation Of Objects Using Only Nouns IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a combination of DL methods for object detection and natural language processing to validate image’s captions. |
Leonardo Anjoletto Ferreira; Douglas De Rizzo Meneghetti; Paulo Eduardo Santos; | arxiv-cs.CV | 2020-10-02 |
| 408 | MultiCQA: Zero-Shot Transfer Of Self-Supervised Text Matching Models On A Massive Scale IF:2 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; | arxiv-cs.CL | 2020-10-02 |
| 409 | LiveQA: A Question Answering Dataset Over Sports Live IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce LiveQA, a new question answering dataset constructed from play-by-play live broadcast. We release the code and data of this paper for future research. |
Qianying Liu; Sicong Jiang; Yizhong Wang; Sujian Li; | arxiv-cs.CL | 2020-10-01 |
| 410 | Towards Question-Answering As An Automatic Metric For Evaluating The Content Quality Of A Summary IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform an extensive evaluation of a QA-based metric for summary content quality, calculating its performance with today’s state-of-the-art models as well as estimating its potential upper-bound performance. |
Daniel Deutsch; Tania Bedrax-Weiss; Dan Roth; | arxiv-cs.CL | 2020-10-01 |
| 411 | 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 Martin Eisenschlos; Syrine Krichene; Thomas Müller; | arxiv-cs.CL | 2020-10-01 |
| 412 | Beyond The Text: Analysis Of Privacy Statements Through Syntactic And Semantic Role Labeling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe 4 different types of conventional methods that can be partially adapted to address the parameter extraction task with varying degrees of success: Hidden Markov Models, BERT fine-tuned models, Dependency Type Parsing (DP) and Semantic Role Labeling (SRL). |
Yan Shvartzshnaider; Ananth Balashankar; Vikas Patidar; Thomas Wies; Lakshminarayanan Subramanian; | arxiv-cs.CL | 2020-10-01 |
| 413 | ISAAQ — Mastering Textbook Questions With Pre-trained Transformers And Bottom-Up And Top-Down Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Textbook Question Answering is a complex task in the intersection of Machine Comprehension and Visual Question Answering that requires reasoning with multimodal information from … |
Jose Manuel Gomez-Perez; Raul Ortega; | arxiv-cs.CL | 2020-10-01 |
| 414 | Stochastic Precision Ensemble: Self-Knowledge Distillation For Quantized Deep Neural Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose stochastic precision ensemble training for QDNNs (SPEQ). |
Yoonho Boo; Sungho Shin; Jungwook Choi; Wonyong Sung; | arxiv-cs.LG | 2020-09-30 |
| 415 | Explainable Natural Language Reasoning Via Conceptual Unification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an abductive framework for multi-hop and interpretable textual inference. |
Marco Valentino; Mokanarangan Thayaparan; André Freitas; | arxiv-cs.AI | 2020-09-30 |
| 416 | Bridging Information-Seeking Human Gaze And Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, we collect a new eye-tracking dataset with a large number of participants engaging in a multiple choice reading comprehension task. |
Jonathan Malmaud; Roger Levy; Yevgeni Berzak; | arxiv-cs.CL | 2020-09-30 |
| 417 | Graph-based Heuristic Search For Module Selection Procedure In Neural Module Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In consideration of this, we proposed a new learning framework for NMN. |
Yuxuan Wu; Hideki Nakayama; | arxiv-cs.AI | 2020-09-30 |
| 418 | A Vietnamese Dataset For Evaluating Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we propose a new process of dataset creation for Vietnamese MRC. Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (UIT-ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models. |
Kiet Van Nguyen; Duc-Vu Nguyen; Anh Gia-Tuan Nguyen; Ngan Luu-Thuy Nguyen; | arxiv-cs.CL | 2020-09-30 |
| 419 | Sequence-to-Sequence Learning For Indonesian Automatic Question Generator IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we construct an Indonesian automatic question generator, adapting the architecture from some previous works. |
Ferdiant Joshua Muis; Ayu Purwarianti; | arxiv-cs.CL | 2020-09-29 |
| 420 | A Survey On Semantic Parsing From The Perspective Of Compositionality IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the following section after an introduction of the field of semantic parsing and its uses in KBQA, we will describe meaning representation using grammar formalism CCG (Steedman, 1996). |
Pawan Kumar; Srikanta Bedathur; | arxiv-cs.CL | 2020-09-29 |
| 421 | Neural Retrieval For Question Answering With Cross-Attention Supervised Data Augmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a supervised data mining method using an accurate early fusion model to improve the training of an efficient late fusion retrieval model. |
Yinfei Yang; Ning Jin; Kuo Lin; Mandy Guo; Daniel Cer; | arxiv-cs.CL | 2020-09-29 |
| 422 | MaP: A Matrix-based Prediction Approach To Improve Span Extraction In Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach that extends the probability vector to a probability matrix. |
Huaishao Luo; Yu Shi; Ming Gong; Linjun Shou; Tianrui Li; | arxiv-cs.CL | 2020-09-29 |
| 423 | What Disease Does This Patient Have? A Large-scale Open Domain Question Answering Dataset From Medical Exams IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. |
DI JIN et. al. | arxiv-cs.CL | 2020-09-28 |
| 424 | Hierarchical Deep Multi-modal Network For Medical Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We evaluate the performance of our proposed model on two benchmark datasets, viz. |
Deepak Gupta; Swati Suman; Asif Ekbal; | arxiv-cs.CL | 2020-09-27 |
| 425 | SPARTA: Efficient Open-Domain Question Answering Via Sparse Transformer Matching Retrieval IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. |
Tiancheng Zhao; Xiaopeng Lu; Kyusong Lee; | arxiv-cs.CL | 2020-09-27 |
| 426 | Unsupervised Pre-training For Biomedical Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To further improve unsupervised representations for biomedical QA, we introduce a new pre-training task from unlabeled data designed to reason about biomedical entities in the context. |
VAISHNAVI KOMMARAJU et. al. | arxiv-cs.CL | 2020-09-27 |
| 427 | KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graph augmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output. |
Ye Liu; Yao Wan; Lifang He; Hao Peng; Philip S. Yu; | arxiv-cs.CL | 2020-09-26 |
| 428 | Techniques To Improve Q&A Accuracy With Transformer-based Models On Large Complex Documents IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper takes a scientific approach to determine the benefits and effectiveness of various techniques and concludes a best-fit combination that produces a statistically significant improvement in accuracy. |
Chejui Liao; Tabish Maniar; Sravanajyothi N; Anantha Sharma; | arxiv-cs.CL | 2020-09-26 |
| 429 | XTE: Explainable Text Entailment IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce XTE – Explainable Text Entailment – a novel composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. |
Vivian S. Silva; André Freitas; Siegfried Handschuh; | arxiv-cs.CL | 2020-09-25 |
| 430 | Machine Knowledge: Creation And Curation Of Comprehensive Knowledge Bases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To support the long-term life-cycle and the quality assurance of machine knowledge, the article presents methods for constructing open schemas and for knowledge curation. |
Gerhard Weikum; Luna Dong; Simon Razniewski; Fabian Suchanek; | arxiv-cs.AI | 2020-09-24 |
| 431 | AliMe KG: Domain Knowledge Graph Construction And Application In E-commerce Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the paper, we systematically introduce how we construct domain knowledge graph from free text, and demonstrate its business value with several applications. |
FENG-LIN LI et. al. | arxiv-cs.AI | 2020-09-24 |
| 432 | Multiple Interaction Learning With Question-type Prior Knowledge For Constraining Answer Search Space In Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel VQA model that utilizes the question-type prior information to improve VQA by leveraging the multiple interactions between different joint modality methods based on their behaviors in answering questions from different types. |
TUONG DO et. al. | arxiv-cs.CV | 2020-09-23 |
| 433 | Using The Hammer Only On Nails: A Hybrid Method For Evidence Retrieval For Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Learning from this probing analysis, we introduce a hybrid approach for evidence retrieval that combines the advantages of both IR directions. |
Zhengzhong Liang; Yiyun Zhao; Mihai Surdeanu; | arxiv-cs.IR | 2020-09-22 |
| 434 | SQuARE: Semantics-based Question Answering And Reasoning Engine IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A question posed against that text is converted into an ASP query using the same framework and executed using the s(CASP) goal-directed ASP system. |
Kinjal Basu; Sarat Chandra Varanasi; Farhad Shakerin; Gopal Gupta; | arxiv-cs.AI | 2020-09-21 |
| 435 | Towards Quantum Belief Propagation For LDPC Decoding In Wireless Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Quantum Belief Propagation (QBP), a Quantum Annealing (QA) based decoder design for Low Density Parity Check (LDPC) error control codes, which have found many useful applications in Wi-Fi, satellite communications, mobile cellular systems, and data storage systems. |
Srikar Kasi; Kyle Jamieson; | mobicom | 2020-09-21 |
| 436 | UCD-CS At W-NUT 2020 Shared Task-3: A Text To Text Approach For COVID-19 Event Extraction On Social Media IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe our approach in the shared task: COVID-19 event extraction from Twitter. |
Congcong Wang; David Lillis; | arxiv-cs.CL | 2020-09-21 |
| 437 | Regularizing Attention Networks For Anomaly Detection In Visual Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we evaluate the robustness of state-of-the-art VQA models to five different anomalies, including worst-case scenarios, the most frequent scenarios, and the current limitation of VQA models. |
Doyup Lee; Yeongjae Cheon; Wook-Shin Han; | arxiv-cs.CV | 2020-09-21 |
| 438 | Can Questions Summarize A Corpus? Using Question Generation For Characterizing COVID-19 Research IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate using question generation models for exploring a collection of documents. |
Gabriela Surita; Rodrigo Nogueira; Roberto Lotufo; | arxiv-cs.IR | 2020-09-19 |
| 439 | Tradeoffs In Sentence Selection Techniques For Open-Domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on approaches which apply an intermediate sentence selection step to address this issue, and investigate the best practices for this approach. |
Shih-Ting Lin; Greg Durrett; | arxiv-cs.CL | 2020-09-18 |
| 440 | Looking Beyond Sentence-Level Natural Language Inference For Downstream Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study this unfulfilled promise from the lens of two downstream tasks: question answering (QA), and text summarization. |
ANSHUMAN MISHRA et. al. | arxiv-cs.CL | 2020-09-18 |
| 441 | A Multimodal Memes Classification: A Survey And Open Research Issues IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a generalized framework for VL problems. |
Tariq Habib Afridi; Aftab Alam; Muhammad Numan Khan; Jawad Khan; Young-Koo Lee; | arxiv-cs.CV | 2020-09-17 |
| 442 | On The Transferability Of Minimal Prediction Preserving Inputs In Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recent work (Feng et al., 2018) establishes the presence of short, uninterpretable input fragments that yield high confidence and accuracy in neural models. |
Shayne Longpre; Yi Lu; Christopher DuBois; | arxiv-cs.CL | 2020-09-17 |
| 443 | ISCAS At SemEval-2020 Task 5: Pre-trained Transformers For Counterfactual Statement Modeling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes our system which is based on pre-trained transformers. |
Yaojie Lu; Annan Li; Hongyu Lin; Xianpei Han; Le Sun; | arxiv-cs.CL | 2020-09-17 |
| 444 | Generation-Augmented Retrieval For Open-domain Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Generation-Augmented Retrieval (GAR), a query expansion method that augments a query with relevant contexts through text generation. |
YUNING MAO et. al. | arxiv-cs.CL | 2020-09-17 |
| 445 | Leveraging Semantic Parsing For Relation Linking Over Knowledge Bases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these challenges, we present SLING, a relation linking framework which leverages semantic parsing using Abstract Meaning Representation (AMR) and distant supervision. |
NANDANA MIHINDUKULASOORIYA et. al. | arxiv-cs.CL | 2020-09-16 |
| 446 | Knowledge Graphs For Multilingual Language Translation And Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this thesis, we focus on the use of KGs for machine translation and the generation of texts to deal with the problems caused by entities and consequently enhance the quality of automatically generated texts. |
Diego Moussallem; | arxiv-cs.CL | 2020-09-16 |
| 447 | Multi-modal Summarization For Video-containing Documents IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence, we propose a novel multi-modal summarization task to summarize from a document and its associated video. Moreover, we collect a novel dataset and it provides a new resource for future study that results from documents and videos. |
Xiyan Fu; Jun Wang; Zhenglu Yang; | arxiv-cs.CL | 2020-09-16 |
| 448 | DDRQA: Dynamic Document Reranking For Open-domain Multi-hop Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose Dynamic Document Reranking (DDR) to iteratively retrieve, rerank and filter documents, and adaptively determine when to stop the retrieval process. |
Yuyu Zhang; Ping Nie; Arun Ramamurthy; Le Song; | arxiv-cs.CL | 2020-09-16 |
| 449 | Self-supervised Pre-training And Contrastive Representation Learning For Multiple-choice Video QA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose novel training schemes for multiple-choice video question answering with a self-supervised pre-training stage and a supervised contrastive learning in the main stage as an auxiliary learning. |
Seonhoon Kim; Seohyeong Jeong; Eunbyul Kim; Inho Kang; Nojun Kwak; | arxiv-cs.CL | 2020-09-16 |
| 450 | Cluster-Former: Clustering-based Sparse Transformer For Long-Range Dependency Encoding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Cluster-Former, a novel clustering-based sparse Transformer to perform attention across chunked sequences. |
SHUOHANG WANG et. al. | arxiv-cs.CL | 2020-09-13 |
| 451 | Receptivity Of An AI Cognitive Assistant By The Radiology Community: A Report On Data Collected At RSNA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, the methodology of the survey is shown and a summary of its results are presented. |
KARINA KANJARIA et. al. | arxiv-cs.AI | 2020-09-13 |
| 452 | A Simple And Efficient Framework For Identifying Relation-gaps In Ontologies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address the above question in this paper. |
Subhashree S; P Sreenivasa Kumar; | arxiv-cs.DB | 2020-09-12 |
| 453 | Towards An Atlas Of Cultural Commonsense For Machine Reasoning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an approach that extends prior work on crowdsourcing commonsense knowledge by incorporating differences in knowledge that are attributable to cultural or national groups. |
Anurag Acharya; Kartik Talamadupula; Mark A Finlayson; | arxiv-cs.AI | 2020-09-11 |
| 454 | FILTER: An Enhanced Fusion Method For Cross-lingual Language Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose FILTER, an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. |
Yuwei Fang; Shuohang Wang; Zhe Gan; Siqi Sun; Jingjing Liu; | arxiv-cs.CL | 2020-09-10 |
| 455 | Accelerating Real-Time Question Answering Via Question Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To accelerate RTQA for practical use, we present Ocean-Q (an Ocean of Questions), a novel approach that leverages question generation (QG) for RTQA. |
Yuwei Fang; Shuohang Wang; Zhe Gan; Siqi Sun; Jingjing Liu; | arxiv-cs.CL | 2020-09-10 |
| 456 | Sanitizing Synthetic Training Data Generation For Question Answering Over Knowledge Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Synthetic data generation is important to training and evaluating neural models for question answering over knowledge graphs. |
Trond Linjordet; Krisztian Balog; | arxiv-cs.IR | 2020-09-10 |
| 457 | Aspect Classification For Legal Depositions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We hypothesize that a legal deposition consists of various aspects that are discussed as part of the deponent testimony. |
Saurabh Chakravarty; Satvik Chekuri; Maanav Mehrotra; Edward A. Fox; | arxiv-cs.CL | 2020-09-09 |
| 458 | E-BERT: A Phrase And Product Knowledge Enhanced Language Model For E-commerce IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the problem, we propose a unified pre-training framework, namely, E-BERT. |
DENGHUI ZHANG et. al. | arxiv-cs.CL | 2020-09-06 |
| 459 | KILT: A Benchmark For Knowledge Intensive Language Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To catalyze research on models that condition on specific information in large textual resources, we present a benchmark for knowledge-intensive language tasks (KILT). |
FABIO PETRONI et. al. | arxiv-cs.CL | 2020-09-04 |
| 460 | A Comparison Of Pre-trained Vision-and-Language Models For Multimodal Representation Learning Across Medical Images And Reports IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we adopt four pre-trained V+L models: LXMERT, VisualBERT, UNIER and PixelBERT to learn multimodal representation from MIMIC-CXR radiographs and associated reports. |
Yikuan Li; Hanyin Wang; Yuan Luo; | arxiv-cs.CV | 2020-09-03 |
| 461 | Multi-Perspective Semantic Information Retrieval IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces the concept of a Multi-Perspective IR system, a novel methodology that combines multiple deep learning and traditional IR models to better predict the relevance of a query-sentence pair, along with a standardized framework for tuning this system. |
Samarth Rawal; Chitta Baral; | arxiv-cs.IR | 2020-09-03 |
| 462 | Revisiting The Open-Domain Question Answering Pipeline IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes Mindstone, an open-domain QA system that consists of a new multi-stage pipeline that employs a traditional BM25-based information retriever, RM3-based neural relevance feedback, neural ranker, and a machine reading comprehension stage. |
Sina J. Semnani; Manish Pandey; | arxiv-cs.CL | 2020-09-02 |
| 463 | Text Modular Networks: Learning To Decompose Tasks In The Language Of Existing Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general approach, Text Modular Networks(TMNs), where the system learns to decompose any complex task into the language of existing models. |
Tushar Khot; Daniel Khashabi; Kyle Richardson; Peter Clark; Ashish Sabharwal; |