Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers

Survey on Machine Reading Comprehension
https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers
List: Reading-Comprehension-Question-Answering-Papers
awesome-list machine-comprehension machine-reading-comprehension mrc-datasets mrc-models qa-over-kg question-answering survey
Last synced: about 1 month ago
JSON representation
Survey on Machine Reading Comprehension
Host: GitHub
URL: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers
Owner: xanhho
Created: 2018-09-02T15:40:06.000Z (over 6 years ago)
Default Branch: master
Last Pushed: 2021-01-26T06:44:37.000Z (almost 4 years ago)
Last Synced: 2024-05-22T22:00:51.674Z (7 months ago)
Topics: awesome-list, machine-comprehension, machine-reading-comprehension, mrc-datasets, mrc-models, qa-over-kg, question-answering, survey
Homepage:
Size: 164 KB
Stars: 150
Watchers: 7
Forks: 15
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

Awesome-Paper-List - Machine Reading Comprehension - xanhho-be8abf) ![](https://img.shields.io/github/stars/xanhho/Reading-Comprehension-Question-Answering-Papers) (Natural Language Processing)
MRCPapers - xanhho / Reading-Comprehension-Question-Answering-Papers - Survey on Machine Reading Comprehension (Repository & Toolkit)
ultimate-awesome - Reading-Comprehension-Question-Answering-Papers - Survey on Machine Reading Comprehension. (Other Lists / PowerShell Lists)
README

        ## Content

- [Survey papers](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#surveyoverview-papersdocuments-should-read-on-machine-reading-comprehension)

- [Slides](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#slides)

- [Evaluation papers](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#evaluation-papers)

- [Models (for single-hop)](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#basic-papersmodels)

- [Knowledge-based Machine Reading Comprehension](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#kbmrc-knowledge-based-machine-reading-comprehension)

- [Open-domain Question Answering](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#opqa-open-domain-question-answering)

- [Unanswerable Questions](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#uq-unanswerable-questions)

- [Multi-Passage Machine Reading Comprehension](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#multi-passage-mrc-multi-passage-machine-reading-comprehension)

- [Conversational Question Answering](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#cqa-conversational-question-answering)

- [Datasets](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#datasets)

- [Datasets with Explanations](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#datasets-with-explanations)

- [QA over KG](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#qa-over-kg)

- [Question answering systems](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#question-answering-systems)

- [Knowledge bases/Knowledge sources](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#knowledge-basesknowledge-sources)

- [Papers misc](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/blob/master/README.md#others-misc-model-transfer-learning-data-augmentation-domain-adaption-cross-lingual-)

## Survey/Overview papers/documents should read on Machine Reading Comprehension

- Fengbin Zhu et al., **Retrieving and Reading : A Comprehensive Survey on Open-domain Question Answering**, arXiv, 2021, [paper](https://arxiv.org/pdf/2101.00774.pdf)

- Mokanarangan Thayaparan, Marco Valentino, and André Freitas, **A Survey on Explainability in Machine Reading Comprehension**, arXiv, 2020, [paper](https://arxiv.org/pdf/2010.00389.pdf)

- Viktor Schlegel et al., **Beyond Leaderboards: A survey of methods for revealing weaknesses in Natural Language Inference data and models**, arXiv, 2020, [paper](https://arxiv.org/pdf/2005.14709.pdf)

- Viktor Schlegel et al., **A Framework for Evaluation of Machine Reading Comprehension Gold Standards**, arXiv, 2020, [paper](https://arxiv.org/pdf/2003.04642.pdf)

- Chengchang Zeng et al., **A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics, and Benchmark Datasets**, arXiv, 2020, [paper](https://arxiv.org/pdf/2006.11880.pdf).

- Razieh Baradaran, Razieh Ghiasi, and Hossein Amirkhani, **A Survey on Machine Reading Comprehension Systems**, arXiv, 6 Jan 2020, [paper](https://arxiv.org/abs/2001.01582).

- Matthew Gardner et al., **On Making Reading Comprehension More Comprehensive.**, aclweb, 2019, [paper](https://www.aclweb.org/anthology/D19-5815.pdf).

- Shanshan Liu et al., **Neural Machine Reading Comprehension: Methods and Trends**, arXiv, 2019, [paper](https://arxiv.org/pdf/1907.01118.pdf).

- Xin Zhang et al., **Machine Reading Comprehension: a Literature Review**, arXiv, 2019, [paper](https://arxiv.org/pdf/1907.01686.pdf).

- Boyu Qiu et al., **A Survey on Neural Machine Reading Comprehension**, arXiv, 2019, [paper](https://arxiv.org/pdf/1906.03824.pdf).

- Danqi Chen: **Neural Reading Comprehension and Beyond**. PhD thesis, Stanford University, 2018, [paper](https://github.com/danqi/thesis).

## Slides

- Sebastian Riedel, Reading and Reasoning with Neural Program Interpreters, [slides](https://mrqa2018.github.io/slides/sebastian.pdf), MRQA 2018.

- Phil Blunsom, Data driven reading comprehension: successes and limitations, [slides](https://mrqa2018.github.io/slides/phil.pdf), MRQA 2018.

- Jianfeng Gao, Multi-step reasoning neural networks for question answering, [slides](https://mrqa2018.github.io/slides/jianfeng.pdf), MRQA 2018.

- Sameer Singh, Questioning Question Answering Answers, [slides](https://mrqa2018.github.io/slides/sameer.pdf), MRQA 2018.

## Evaluation papers

- Diana Galvan, **Active Reading Comprehension: A dataset for learning the Question-Answer Relationship strategy**, ACL 2019, [paper](https://www.aclweb.org/anthology/P19-2014).

- Divyansh Kaushik and Zachary C. Lipton, **How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks**, EMNLP 2018, [paper](https://www.aclweb.org/anthology/D18-1546.pdf).

- Saku Sugawara et al., **What Makes Reading Comprehension Questions Easier?**, EMNLP 2018, [paper](https://www.aclweb.org/anthology/D18-1453.pdf).

- Pramod K. Mudrakarta et al., **Did the Model Understand the Question?**, ACL 2018, [paper](https://www.aclweb.org/anthology/P18-1176.pdf).

- Robin Jia and Percy Liang, **Adversarial Examples for Evaluating Reading Comprehension Systems**, EMNLP 2017, [paper](https://www.aclweb.org/anthology/D17-1215.pdf).

- Saku Sugawara et al., **Evaluation Metrics for Machine Reading Comprehension: Prerequisite Skills and Readability**, ACL 2017, [paper](https://www.aclweb.org/anthology/P17-1075.pdf).

- Saku Sugawara et al., **Prerequisite Skills for Reading Comprehension: Multi-perspective Analysis of MCTest Datasets and Systems**, AAAI 2017, [paper](http://www.aaai.org/Conferences/AAAI/2017/PreliminaryPapers/14-Sugawara-14614.pdf).

- Danqi Chen et al., **A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task**, ACL 2016, [paper](https://www.aclweb.org/anthology/P16-1223.pdf).

## Basic Papers/Models

| Year | Title | Model| Datasets | Misc                                                                  | Paper, Source Code |

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| 2019 | XLNet: Generalized Autoregressive Pretraining for Language Understanding | XLNet | Race, SQuAD 1.1, SQuAD 2.0 | pretrained LM  | [paper](https://arxiv.org/pdf/1906.08237.pdf), [code](https://github.com/zihangdai/xlnet/) |

| 2019 | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | BERT | GLUE, SQuAD 1.1, SQuAD 2.0, SWAG | pretrained LM | [paper](https://www.aclweb.org/anthology/N19-1423), [code](https://github.com/google-research/bert) |

| 2018 | S-NET: From Answer Extraction to Answer Generation for Machine Reading Comprehension | S-NET | MS-MARCO  | multiple passages | [paper](https://arxiv.org/pdf/1706.04815.pdf), [code]|

| 2018 | QANET: Combining local Convolution with global Self-Attention for Reading Comprehension | QANet |  SQuAD 1.1 |  | [paper](https://openreview.net/pdf?id=B14TlG-RW), [code](https://github.com/google-research/google-research/tree/master/qanet) |

| 2017 | ReasoNet: Learning to Stop Reading in Machine Comprehension | ReasoNet | CNN and Daily Mail, SQuAD 1.1 |  | [paper](https://arxiv.org/pdf/1609.05284.pdf), [code] |

| 2017 | Reading Wikipedia to Answer Open-Domain Questions | DrQA |  Wikipedia, SQuAD 1.1, CuratedTREC, WebQuestions, WikiMovies | OPQA, Multi-Passage MRC | [paper](https://www.aclweb.org/anthology/P17-1171), [code](https://github.com/facebookresearch/DrQA) |

| 2017 | R-Net: Machine Reading Comprehension with Self-Matching Networks | R-Net |  SQuAD 1.1, MS-MARCO |  | [paper](https://www.microsoft.com/en-us/research/wp-content/uploads/2017/05/r-net.pdf), [code](https://github.com/HKUST-KnowComp/R-Net) |

| 2017 | Machine Comprehension Using Match-LSTM and Answer Pointer | Match-LSTM + Pointer Network| SQuAD 1.1 |  | [paper](https://arxiv.org/pdf/1608.07905.pdf), [code](https://github.com/shuohangwang/SeqMatchSeq) |

| 2017 | Gated-Attention Readers for Text Comprehension | Gated-attention Reader | CNN and Daily Mail, Children’s Book Test, Who Did What |  | [paper](https://arxiv.org/pdf/1606.01549.pdf), [code](https://github.com/bdhingra/ga-reader) |

| 2017 | Gated Self-Matching Networks for Reading Comprehension and Question Answering | Gated Self-Matching | SQuAD 1.1 |  | [paper](https://www.aclweb.org/anthology/P17-1018.pdf), [code] |

| 2017 | Dynamic CoAttention Networks for Question Answering | Dynamic coattention networks | SQuAD 1.1 |  | [paper](https://arxiv.org/pdf/1611.01604.pdf), [code](https://github.com/thomasfermi/Dynamic-Coattention-Network-for-SQuAD) |

| 2017 | DCN+: Mixed Objective and Deep Residual CoAttention for Question Answering | DCN+ | SQuAD 1.1 |  | [paper](https://arxiv.org/pdf/1711.00106.pdf), [code](https://github.com/andrejonasson/dynamic-coattention-network-plus) |

| 2017 | Bi-directional Attention Flow for Machine Comprehension | BiDAF | SQuAD 1.1 |  | [paper](https://arxiv.org/pdf/1611.01603.pdf), [code](https://github.com/allenai/bi-att-flow) |

| 2017 | Attention-over-Attention Neural Networks for Reading Comprehension | Attention-over-Attention Reader | Children’s Book Test, CNN and Daily Mail |  | [paper](https://www.aclweb.org/anthology/P17-1055.pdf), [code](https://github.com/OlavHN/attention-over-attention)|

| 2016 | Text Understanding with the Attention Sum Reader Network | Attention Sum Reader | Children’s Book Test, CNN and Daily Mail |  | [paper](https://www.aclweb.org/anthology/P16-1086), [code](https://github.com/rkadlec/asreader) |

| 2016 | Multi-Perspective Context Matching for Machine Comprehension | Multi-Perspective Context Matching | SQuAD 1.1 |  | [paper](https://arxiv.org/pdf/1612.04211.pdf), [code] |

| 2016 | Key-Value Memory Networks for Directly Reading Documents | Key-Value Memory Networks | WikiMovies, WikiQA |  | [paper](https://aclweb.org/anthology/D16-1147/), [code](https://github.com/facebook/MemNN/tree/master/KVmemnn) |

| 2016 | Iterative Alternating Neural Attention for Machine Reading | Iterative Attention Reader | Children’s Book Test, CNN and Daily Mail |  | [paper](https://arxiv.org/pdf/1606.02245.pdf), [code]|

| 2016 | A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task |  | CNN and Daily Mail |  | [paper](https://www.aclweb.org/anthology/P16-1223.pdf), [code] |

| 2015 | Teaching Machines to Read and Comprehend | Attentive Reader | CNN and Daily Mail |  | [paper](https://papers.nips.cc/paper/5945-teaching-machines-to-read-and-comprehend.pdf), [code](https://github.com/thomasmesnard/DeepMind-Teaching-Machines-to-Read-and-Comprehend) |

## KBMRC: Knowledge-based Machine Reading Comprehension

  * Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/Knowledge-based-MRC 

  

##  OPQA: Open-domain Question Answering

  * Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/Open-domain-Question-Answering

  

##  UQ: Unanswerable Questions

  * Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/Unanswerable-Questions

  

##  Multi-Passage MRC: Multi-Passage Machine Reading Comprehension

  * Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/Multi-Passage-MRC

  

##  CQA: Conversational Question Answering

  * Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/CQA

## Datasets

- Following Danqi Chen, we have four answer types: 

  * Cloze test

  * Multiple choice

  * Span extraction

  * Free answering

- Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/MRC-Datasets

| Year | Dataset | Task | Size | Source | Web/Paper | Answer type                                                                  | Misc | Similar datasets |

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| 2019 | ROPES | RC | 14k | Wikipedia + science textbooks | [web](https://allennlp.org/ropes), [paper](https://arxiv.org/pdf/1908.05852.pdf) | Span extraction | background passage + situation | ShARC |

|2019| RC-QED | RC | 12k | Wikipedia |[web](https://naoya-i.github.io/rc-qed/), [paper](https://arxiv.org/pdf/1910.04601.pdf)| Multiple choice  | multi-passage | HotpotQA |

|2019| QUOREF| RC | 24k+ | Wikipedia |[web](https://allennlp.org/quoref), [paper](https://www.aclweb.org/anthology/D19-1606.pdf)| Span extraction | coreference resolution |  |

|2019| COSMOS QA|  | 35,600 | narrative |[web](https://wilburone.github.io/cosmos/), [paper](https://www.aclweb.org/anthology/D19-1243.pdf)| Multiple choice  |  |  |

|2019| DROP | RC | 96k | Wikipedia | [web](https://allennlp.org/drop), [paper](https://arxiv.org/pdf/1903.00161.pdf) | Span extraction + numerical reasoning | multi-span answers | |

|2019| Natural Questions | RC | 323k | Wikipedia | [paper](https://www.aclweb.org/anthology/Q19-1026.pdf) | Span extraction | | |

|2018|SQuAD 2.0| RC | 150k | Wikipedia |[paper](https://rajpurkar.github.io/SQuAD-explorer/)| Span extraction | no answer: 50k | NewsQA |

|2018|MultiRC| RC | 6k+ questions | various articles | [web](https://cogcomp.seas.upenn.edu/multirc/), [paper](https://www.aclweb.org/anthology/N18-1023)| Multiple choice  | multiple sentence reasoning | MCTest |

|2018|CSQA| QA |200k dialogs, 1.6M turns ||[paper](https://arxiv.org/pdf/1801.10314.pdf)|  |  |  |

|2018| QuAC | RC | 100k | Wikipedia |[web](http://quac.ai/), [paper](https://arxiv.org/pdf/1808.07036.pdf) | Span extraction | conversational questions | CoQA |

|2018| QAngaroo (Wikihop + Medhop) | RC |  | Wikipedia + Medline |[web](https://qangaroo.cs.ucl.ac.uk/), [paper](https://transacl.org/ojs/index.php/tacl/article/viewFile/1325/299)| Multiple choice | multi-passage | HotpotQA |

|2018| HotpotQA | RC | 113k | Wikipedia |[web](https://hotpotqa.github.io/), [paper](https://arxiv.org/pdf/1809.09600.pdf)| Span extraction | multi-passage | QAngaroo |

|2018| CoQA | RC | 127k | various articles |[paper](https://stanfordnlp.github.io/coqa/)| Free answering | conversational questions | QuAC |

|2018| ComplexWebQuestions | RC | 34,689 | WebQuestionsSP |[web](https://www.tau-nlp.org/compwebq), [paper](https://www.aclweb.org/anthology/N18-1059.pdf)| Span extraction? | multi-passage |  |

| 2018 | SWAG | QA | 113k | video caption |  | Multiple choice | situational commonsense reasoning |  |

| 2018 | RecipeQA | RC | 36k | various |  |  | multimodal comprehension |  |

| 2018 | ProPara | RC | 2k | procedural text |  |  |  | bAbI, SCoNE |

| 2018 | OpenBookQA | QA | 6k | science facts |  | Multiple choice  | external knowledge | ARC |

| 2018 | FEVER |  |  |  |  |  |  | |

| 2018 | DuReader |  |  |  |  | Free answering |  |  |

| 2018 | DuoRC | RC | 186k | movie plot |  | Span extraction |  | NarrativeQA  |

| 2018 | CLOTH | RC | 99k | English exams |  | Cloze test |  | RACE |

| 2018 | CliCR | RC | 100k | clinical case text |  | Cloze test |  |  |

| 2018 | ARC | RC | 8k | science exam |  |  | easy 5197, challenge 2590 | |

|2017|WikiSuggest||||[paper](https://aclweb.org/anthology/D15-1237)|  |  | |

|2017|TriviaQA| RC | 96k question-answer pairs | Web + Wikipedia | [web](http://nlp.cs.washington.edu/triviaqa/), [paper](https://arxiv.org/pdf/1705.03551.pdf) | Span extraction | | SQuAD |

|2017|SQA||||[paper](https://people.cs.umass.edu/~miyyer/pubs/2017_acl_dynsp.pdf)|  |  | |

|2017|SearchQA||||[paper](https://arxiv.org/pdf/1704.05179.pdf)| Free answering |  | |

|2017|RACE||||[paper](http://www.cs.cmu.edu/~glai1/data/race/)| Multiple choice |  | |

|2017|NarrativeQA||||[paper](https://github.com/deepmind/narrativeqa)| Free answering |  |  |

|2016|Who-did-What||||[paper](https://tticnlp.github.io/who_did_what/)| Cloze test |  | |

|2016|SQuAD 1.1| RC | 87k training + 10k development | Wikipedia |[paper](https://rajpurkar.github.io/SQuAD-explorer/)| Span extraction |  | NewsQA |

|2016|NewsQA||||[paper](https://datasets.maluuba.com/NewsQA)| Span extraction |  |  |

|2016|MS MARCO||||[web](http://www.msmarco.org/dataset.aspx)| Free answering |  |  |

|2016|LAMBADA||||[paper](http://clic.cimec.unitn.it/lambada/)| Cloze test |  | |

| 2016 | WikiMovies | QA |  |  |  | |  |  |

| 2015 | CuratedTREC | QA |  |  |  | |  |  |

|2015|CNN and Daily Mail| RC | 93k + 220k articles| CNN + Daily Mail |[paper](https://papers.nips.cc/paper/5945-teaching-machines-to-read-and-comprehend.pdf) [web](https://cs.nyu.edu/~kcho/DMQA/)| Cloze test |  |  |

|2015|Children's Book Test| RC | 108 children's books | |[web](https://research.fb.com/downloads/babi/)| Cloze test |  | |

|2015|bAbI| RC | | classic text adventure game |[web](https://research.fb.com/downloads/babi/)| Free answering | 20 tasks |  |

| 2013 | WebQuestions | QA |  |  |  | |  |  |

|2013|QA4MRE| RC | | various articles |[paper](https://www.cs.cmu.edu/~hovy/papers/13CLEF-QA4MRE.pdf)| Multiple choice |  | |

|2013|MCTest| RC | 500 stories + 2k questions | fictional stories |[paper](http://aclweb.org/anthology/D13-1020)| Multiple choice | open-domain  |  |

|1999|DeepRead| RC | 60 development and 60 test? | news stories|[paper](https://dl.acm.org/citation.cfm?id=1034678.1034731)| Free answering |  |  |

## Datasets with Explanations

 * Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/Datasets-with-Explanations

 

 ## QA over KG

 * Details: https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers/wiki/QA-over-KG

## Knowledge Bases/Knowledge Sources

- Wikidata, [web](https://www.wikidata.org/wiki/Wikidata:Main_Page)

- Freebase, [paper](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.538.7139&rep=rep1&type=pdf)

- DBPedia

## Question Answering Systems

- IBM's DeepQA

- QuASE

- Microsoft's AskMSR

- YodaQA

- DrQA

## Others (Misc: Model, transfer learning, data augmentation, domain adaption, cross lingual ...)

- Minghao Hu, Yuxing Peng, Zhen Huang and Dongsheng Li, **A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1170.pdf).

- Huazheng Wang, Zhe Gan, Xiaodong Liu, Jingjing Liu, Jianfeng Gao and Hongning Wang, **Adversarial Domain Adaptation for Machine Reading Comprehension**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1254.pdf).

- Yimin Jing, Deyi Xiong and Zhen Yan, **BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1249.pdf).

- Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang and Guoping Hu, **Cross-Lingual Machine Reading Comprehension**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1169.pdf).

- Todor Mihaylov and Anette Frank, **Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1257.pdf).

- Kyungjae Lee, Sunghyun Park, Hojae Han, Jinyoung Yeo, Seung-won Hwang and Juho Lee, **Learning with Limited Data for Multilingual Reading Comprehension**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1283.pdf).

- Qiu Ran, Yankai Lin, Peng Li, Jie Zhou and Zhiyuan Liu, **NumNet: Machine Reading Comprehension with Numerical Reasoning**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1251.pdf).

- Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang and Guoping Hu, **A Span-Extraction Dataset for Chinese Machine Reading Comprehension**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1600.pdf).

- Daniel Andor, Luheng He, Kenton Lee and Emily Pitler, **Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1609.pdf).

- Tsung-Yuan Hsu, Chi-Liang Liu and Hung-yi Lee, **Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model**, EMNLP 2019, [paper](https://www.aclweb.org/anthology/D19-1607.pdf).

- Kyosuke Nishida et al., **Multi-style Generative Reading Comprehension**, ACL 2019, [paper](https://www.aclweb.org/anthology/P19-1220).

- Alon Talmor and Jonathan Berant, **MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension**, ACL 2019, [paper](https://www.aclweb.org/anthology/P19-1485).

- Yi Tay et al., **Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives**, ACL 2019, [paper](https://www.aclweb.org/anthology/P19-1486).

- Haichao Zhu et al., **Learning to Ask Unanswerable Questions for Machine Reading Comprehension**, ACL 2019, [paper](https://www.aclweb.org/anthology/P19-1415).

- Patrick Lewis et al., **Unsupervised Question Answering by Cloze Translation**, ACL 2019, [paper](https://www.aclweb.org/anthology/P19-1484.pdf). 

- Michael Hahn and Frank Keller, **Modeling Human Reading with Neural Attention**, EMNLP 2016, [paper](https://www.aclweb.org/anthology/D16-1009.pdf).

- Jianpeng Cheng et al., **Long Short-Term Memory-Networks for Machine Reading**, EMNLP 2016, [paper](https://www.aclweb.org/anthology/D16-1053.pdf).

## Thanks to these repositories:

- https://github.com/penzant/nlu_datasets_2018

- https://github.com/seriousmac/awesome-qa