Machine Reading Comprehension and Question Answering

Theses

[2018 Stanford University] Neural Reading Comprehension and Beyond, [thesis], [copy], [bibtex], author: [Danqi Chen].

Datasets

[2013 EMNLP] MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text, [paper], [bibtex], [homepage], source: [mcobzarenco/mctest].
[2015 NIPS] CNN/DailyMail: Teaching Machines to Read and Comprehend, [paper], [bibtex], [homepage], sources: [thomasmesnard/DeepMind-Teaching-Machines-to-Read-and-Comprehend].
[2016 EMNLP] SQuAD 100,000+ Questions for Machine Comprehension of Text, [paper], [bibtex], [homepage].
[2016 ICLR] bAbI: Towards AI-Complete Question Answering: a Set of Prerequisite Toy Tasks, [paper], [bibtex], [homepage], sources: [facebook/bAbI-tasks].
[2017 EMNLP] World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions, [paper], [bibtex], [homepage].
[2017 EMNLP] RACE: Large-scale ReAding Comprehension Dataset From Examinations, [paper], [bibtex], [homepage], sources: [qizhex/RACE_AR_baselines].
[2017 ACL] TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension, [paper], [bibtex] [homepage], sources: [mandarjoshi90/triviaqa].
[2018 TACL] QAngaroo: Constructing Datasets for Multi-hop Reading Comprehension Across Documents, [paper], [bibtex], [homepage].
[2018 ACL] Know What You Don’t Know: Unanswerable Questions for SQuAD, [paper], [bibtex], [supplementary], [homepage], sources: [CodaLab Worksheet].
[2018 ICLR] CLOTH: Large-scale Cloze Test Dataset Designed by Teachers, [paper], [bibtex], [homepage], sources: [qizhex/Large-scale-Cloze-Test-Dataset-Designed-by-Teachers].
[2018 NAACL] (MultiRC) Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences, [paper], [bibtex], [homepage], sources: [CogComp/multirc].
[2018 EMNLP] HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering, [paper], [bibtex], [attachment], [homepage], sources: [hotpotqa/hotpot].
[2019 NAACL] CommonsenseQA: A Question Answering Challenge Targeting, [paper], [bibtex], [homepage], sources: [jonathanherzig/commonsenseqa].
[2019 EMNLP] COSMOS QA: Machine Reading Comprehension with Contextual Commonsense Reasoning, [paper], [bibtex], [homepage].
[2019 TACL] Natural Questions: a Benchmark for Question Answering Research, [paper], [bibtex], [homepage], sources: [google-research-datasets/natural-questions].
[2020 ACL] MLQA: Evaluating Cross-lingual Extractive Question Answering, [paper], [bibtex], sources: [acebookresearch/MLQA].
[2020 ACL] On the Cross-lingual Transferability of Monolingual Representations, [paper], [bibtex], sources: [deepmind/xquad].
[2020 TACL] TYDI QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages, [paper], [bibtex], [homepage], sources: [google-research-datasets/tydiqa].
[2020 ICML] XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization, [paper], [bibtex], [supplementary], [homepage], sources: [google-research/xtreme].
[2020 ICLR] ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning, [paper], [bibtex], [homepage], sources: [yuweihao/reclor].
[2020 IJCAI] LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning, [paper], [bibtex], sources: [lgw863/LogiQA-dataset].
[2020 EMNLP] TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions, [paper], [bibtex], [homepage].

Methods

[2014 NIPS] Deep Learning for Answer Sentence Selection, [paper], [bibtex], sources: [brmson/Sentence-selection].
[2014 ACL] Freebase QA: Information Extraction or Semantic Parsing?, [paper], [bibtex].
[2015 IJCAI] Convolutional Neural Tensor Network Architecture for Community-based Question Answering, [paper], [bibtex], sources: [GauravBh1010tt/DeepLearn], [SongRb/Seq2SeqLearning].
[2015 NIPS] Pointer Networks, [paper], [bibtex], [blog], sources: [devsisters/pointer-network-tensorflow], [https://github.com/ikostrikov/TensorFlow-Pointer-Networks], [keon/pointer-networks], [pemami4911/neural-combinatorial-rl-pytorch], [shiretzet/PointerNet].
[2016 ACL] Question Answering on Freebase via Relation Extraction and Textual Evidence, [paper], [bibtex], sources: [syxu828/QuestionAnsweringOverFB].
[2016 EMNLP] Long Short-Term Memory-Networks for Machine Reading, [paper], [bibtex], sources: [cheng6076/SNLI-attention], [vsitzmann/snli-attention-tensorflow].
[2016 ICLR] LSTM-based Deep Learning Models for Non-factoid Answer Selection, [paper], [bibtex], sources: [Alan-Lee123/answer-selection], [tambetm/allenAI].
[2016 ICML] Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, [paper], [bibtex], sources: [DongjunLee/dmn-tensorflow].
[2016 ACL] A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task, [paper], [bibtex], sources: [danqi/rc-cnn-dailymail].
[2016 ICML] Dynamic Memory Networks for Visual and Textual Question Answering, [paper], [bibtex], [blog], sources: [therne/dmn-tensorflow], [barronalex/Dynamic-Memory-Networks-in-TensorFlow], [ethancaballero/Improved-Dynamic-Memory-Networks-DMN-plus], [dandelin/Dynamic-memory-networks-plus-Pytorch], [DeepRNN/visual_question_answering].
[2017 ICLR] Query-Reduction Networks for Question Answering, [paper], [bibtex], [homepage], sources: [uwnlp/qrn].
[2017 ICLR] Bi-Directional Attention Flow for Machine Comprehension, [paper], [bibtex], [homepage], [demo], sources: [allenai/bi-att-flow].
[2017 KDD] ReasoNet: Learning to Stop Reading in Machine Comprehension, [paper], [bibtex], source: [CNTK/Tutorials/CNTK_302_ReasoNet].
[2017 ACL] Learning to Skim Text, [paper], [bibtex], [notes].
[2017 ACL] R-Net: Machine Reading Comprehension with Self-matching Networks or Gated Self-Matching Networks for Reading Comprehension and Question Answering, [paper], [paper], [bibtex], [blog], sources: [HKUST-KnowComp/R-Net], [YerevaNN/R-NET-in-Keras], [minsangkim142/R-net].
[2017 ICLR] Machine Comprehension Using Match-LSTM and Answer Pointer, [paper], [bibtex], sources: [shuohangwang/SeqMatchSeq], [MurtyShikhar/Question-Answering], [InnerPeace-Wu/reading_comprehension-cs224n].
[2017 EMNLP] Accurate Supervised and Semi-Supervised Machine Reading for Long Documents, [paper], [bibtex].
[2017 CoNLL] Making Neural QA as Simple as Possible but not Simpler, [paper], [bibtex], [homepage], [github-page], sources: [georgwiese/biomedical-qa].
[2017 EMNLP] Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension, [paper], [bibtex], sources: [davidgolub/QuestionGeneration].
[2017 ACL] Attention-over-Attention Neural Networks for Reading Comprehension, [paper], [bibtex], sources: [OlavHN/attention-over-attention], [marshmelloX/attention-over-attention].
[2017 EMNLP] Identifying Where to Focus in Reading Comprehension for Neural Question Generation, [paper], [bibtex].
[2017 ACL] Improved Neural Relation Detection for Knowledge Base Question Answering, [paper], [bibtex].
[2017 ACL] An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge, [paper], [bibtex], [homepage], [blog].
[2017 EMNLP] Learning what to read: Focused machine reading, [paper], [bibtex].
[2017 ACL] Reading Wikipedia to Answer Open-Domain Questions, [paper], [bibtex], sources: [facebookresearch/DrQA], [hitvoice/DrQA].
[2017 CoNLL] Zero-Shot Relation Extraction via Reading Comprehension, [paper], [bibtex], sources: [omerlevy/bidaf_no_answer], [zhuzhicai/SQuAD2.0-Baseline-Test-with-BiDAF-No-Answer].
[2017 AAAI] Cross Temporal Recurrent Networks for Ranking Question Answer Pairs, [paper], [bibtex].
[2018 ICLR] MaskGAN: Better Text Generation via Filling in the ______, [paper], [bibtex].
[2018 AAAI] Multi-attention Recurrent Network for Human Communication Comprehension, [paper], [bibtex].
[2018 IEEE Access] An Attention-Based Word-Level Interaction Model for Knowledge Base Relation Detection, [paper], [bibtex].
[2018 ICLR] FusionNet: Fusing via Fully-aware Attention with Application to Machine Comprehension, [paper], [bibtex], sources: [exe1023/FusionNet], [momohuang/FusionNet-NLI].
[2018 NAACL] Contextualized Word Representations for Reading Comprehension, [paper], [bibtex], sources: [shimisalant/CWR].
[2018 NAACL] Supervised and Unsupervised Transfer Learning for Question Answering, [paper], [bibtex].
[2018 ICLR] QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension or Fast and Accurate Reading Comprehension by Combining Self-Attention and Convolution, [paper], [bibtex], sources: [hengruo/QANet-pytorch], [NLPLearn/QANet].
[2018 ICLR] Neural Speed Reading via Skim-RNN, [paper], [bibtex], sources: [schelotto/Neural_Speed_Reading_via_Skim-RNN_PyTorch].
[2018 SemEval] Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension, [paper], [bibtex], sources: [intfloat/commonsense-rc].
[2018 ACL] Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge, [paper], [bibtex].
[2018 ACL] Stochastic Answer Networks for Machine Reading Comprehension, [paper], [bibtex], sources: [kevinduh/san_mrc].
[2018 EMNLP] Commonsense for Generative Multi-Hop Question Answering Tasks, [paper], [bibtex], sources: [yicheng-w/CommonSenseMultiHopQA].
[2018 NIPS] Densely Connected Attention Propagation for Reading Comprehension, [paper], [bibtex], sources: [vanzytay/NIPS2018_DECAPROP].
[2018 ArXiv] Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading, [paper], [bibtex].
[2018 ArXiv] U-Net: Machine Reading Comprehension with Unanswerable Questions, [paper], [bibtex], sources: [FudanNLP/UNet].
[2018 KDD] Multi-Cast Attention Networks for Retrieval-based Question Answering and Response Prediction, [paper], [bibtex].
[2018 ACL] Simple and Effective Multi-Paragraph Reading Comprehension, [paper], [bibtex], sources: [allenai/document-qa].
[2018 AAAI] Reinforced Ranker-Reader for Open-Domain Question Answering, [paper], [bibtex], sources: [shuohangwang/mprc].
[2018 ICLR] Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering, [paper], [bibtex], sources: [shuohangwang/mprc].
[2018 NAACL] The Web as a Knowledge-base for Answering Complex Questions, [paper], [bibtex].
[2018 EMNLP] A Nil-Aware Answer Extraction Framework for Question Answering, [paper], [bibtex], sources: [nusnlp/namanda].
[2018 ICLR] Ask the Right Questions: Active Question Reformulation with Reinforcement Learning, [paper], [bibtex], sources: [google/active-qa].
[2019 ACL] MULTIQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension, [paper], [bibtex], sources: [alontalmor/MultiQA].
[2019 ACL] Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension, [paper], [bibtex].
[2019 ACL] Synthetic QA Corpora Generation with Roundtrip Consistency, [paper], [bibtex], [Supplementary], sources: [patil-suraj/question_generation].
[2019 AAAI] Read + Verify: Machine Reading Comprehension with Unanswerable Questions, [paper], [bibtex].
[2019 ArXiv] What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?, [paper], [bibtex].
[2019 ArXiv] A BERT Baseline for the Natural Questions, [paper], [bibtex].
[2019 ArXiv] Frustratingly Easy Natural Question Answering, [paper], [bibtex].
[2019 ArXiv] How Additional Knowledge can Improve Natural Language Commonsense Question Answering?, [paper], [bibtex].
[2019 EMNLP] Revealing the Importance of Semantic Retrieval for Machine Reading at Scale, [paper], [bibtex], sources: [easonnie/semanticRetrievalMRS].
[2019 EMNLP] Evaluating Question Answering Evaluation, [paper], [bibtex].
[2020 AAAI] MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension, [paper], [bibtex].
[2020 AAAI] Unsupervised Domain Adaptation on Reading Comprehension, [paper], [bibtex], sources: [caoyu1991/CASe].
[2020 AAAI] SG-Net: Syntax-Guided Machine Reading Comprehension, [paper], [bibtex], sources: [cooelf/SG-Net].
[2020 ICLR] Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention, [paper], [bibtex], sources: [microsoft/Transformer-XH].
[2020 ACL] Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering, [paper], [bibtex].
[2020 ACL] RikiNet: Reading Wikipedia Pages for Natural Question Answering, [paper], [bibtex].
[2020 ACL] Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases, [paper], [bibtex], sources: [lanyunshi/Multi-hopComplexKBQA].
[2020 ACL] Dice Loss for Data-imbalanced NLP Tasks, [paper], [bibtex], sources: [ShannonAI/dice_loss_for_NLP].
[2020 ACL] Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension, [paper], [bibtex].
[2020 SIGIR] DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding, [paper], [bibtex], sources: [gitabtion/DerivativeBertModels].
[2020 EMNLP] UnifiedQA: Crossing Format Boundaries With a Single QA System, [paper], [bibtex], sources: [allenai/unifiedqa].
[2020 EMNLP] Zero-Shot Cross-Lingual Transfer with Meta Learning, [paper], [bibtex], sources: [copenlu/X-MAML].
[2020 EMNLP] A Simple and Effective Model for Answering Multi-span Questions, [paper], [bibtex], sources: [eladsegal/tag-based-multi-span-extraction].
[2020 ArXiv] Answering Any-hop Open-domain Questions with Iterative Document Reranking, [paper], [bibtex].
[2020 ArXiv] Counterfactual Variable Control for Robust and Interpretable Question Answering, [paper], [bibtex], sources: [PluviophileYU/CVC-QA].
[2021 NAACL] RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering, [paper], [bibtex], sources: [PaddlePaddle/NAACL2021-RocketQA].
[2021 ACL] Why Machine Reading Comprehension Models Learn Shortcuts?, [paper], [bibtex], sources: [luciusssss/why-learn-shortcut].
[2021 ACL] Syntax-augmented Multilingual BERT for Cross-lingual Transfer, [paper], [bibtex], sources: [wasiahmad/Syntax-MBERT].
[2021 ACL] Consistency Regularization for Cross-Lingual Fine-Tuning, [paper], [bibtex], sources: [bozheng-hit/xTune].