多轮问答（document based dialogue）
DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension https://dataset.org/ dream/.
Challenging reading comprehension on daily conversation: Passage completion on mul- tiparty dialog.
QuAC: Question an- swering in context
A Dataset for Document Grounded Conversations
OF WIKIPEDIA:
KNOWLEDGE-POWERED CONVERSATIONAL AGENTS
Towards Exploiting Background Knowledge for Building Conversation Systems
综述
A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC
Emergent Logical Structure in Vector Representations of Neural Readers[https://arxiv.org/pdf/1611.07954v1.pdf]
机器阅读理解任务综述 林鸿宇 韩先培[https://mp.weixin.qq.com/s?__biz=MzIxNzE2MTM4OA==&mid=2665643130&idx=1&sn=5f75f0d4978289caea6c4cb37b0b74c4\]
自动问答综述 郑实福， 刘挺， 秦兵， 李生 - 中文信息学报
面向问答社区的答案摘要方法研究综述 刘秉权， 徐振， 刘峰， 刘铭， 孙承杰， 王晓龙 - 中文信息学报
问答系统综述 李沛晏， 朱露， 吴多胜 - 数字技术与应用
特定领域问答系统中基于语义检索的非事实型问题研究仇瑜， 程力 - 北京大学学报 (自然科学版), 2019
基于汉语篇章框架语义分析的阅读理解问答研究
王智强， 李茹， 梁吉业， 张旭华， 武娟， 苏娜 - 计算机学报
基于 Web 的问答系统综述 李舟军， 李水华 - 计算机科学, 2017
智能问答系统在医学领域的应用研究 贺佳， 杜建强， 聂斌， 熊旺平， 罗计根 - 医学信息, 2018
基于粗糙集知识发现的开放领域中文问答检索
韩朝， 苗夺谦， 任福继， 张红云 - 计算机研究与发展, 201
Datasets
MCTest
http://research.microsoft.com/en-us/um/redmond/projects/mctest/data.html
bAbI
https://research.fb.com/projects/babi/
WikiQA
https://www.microsoft.com/en-us/download/details.aspx?id=52419
SNLI
http://nlp.stanford.edu/projects/snli/
Children’s Book Test
https://research.fb.com/projects/babi/
BookTest
https://ibm.ent.box.com/v/booktest-v1
CNN / Daily Mail
http://cs.nyu.edu/~kcho/DMQA/
Who Did What
https://tticnlp.github.io/who_did_what/download.html
NewsQA
http://datasets.maluuba.com/NewsQA
SQuAD
https://rajpurkar.github.io/SQuAD-explorer/
LAMBADA
http://clic.cimec.unitn.it/lambada/
MS MARCO
http://www.msmarco.org/dataset.aspx
WikiMovies
https://research.fb.com/projects/babi/
WikiReading
https://github.com/dmorr-google/wiki-reading
CoQA: A conversational question answering challenge.
SemEval-2018 Task 11: Machine comprehen- sion using commonsense knowledge.
ODSQA: Open-domain spoken question an- swering dataset.
Looking beyond the surface: A challenge set for reading comprehension over multiple sen- tences
SearchQA: A new Q&A dataset augmented with context from a search engine
论文
Teaching Machines to Read and Comprehend
[https://arxiv.org/abs/1506.03340]
Learning to Ask: Neural Question Generation for Reading Comprehension
https://arxiv.org/pdf/1705.00106.pdf
Attention-over-Attention Neural Networks for Reading Comprehension
https://arxiv.org/pdf/1607.04423.pdf
R-NET: MACHINE READING COMPREHENSION WITH SELF-MATCHING NETWORKS
https://www.microsoft.com/en-us/research/wp-content/uploads/2017/05/r-net.pdf
Mnemonic Reader for Machine Comprehension
https://arxiv.org/pdf/1705.02798.pdf
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
https://arxiv.org/pdf/1705.03551.pdf
S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
https://arxiv.org/pdf/1706.04815.pdf
RACE: Large-scale ReAding Comprehension Dataset From Examinations
https://arxiv.org/pdf/1704.04683.pdf
Adversarial Examples for Evaluating Reading Comprehension Systems
https://arxiv.org/pdf/1707.07328.pdf
Machine comprehension using match-lstm and answer pointer
[https://arxiv.org/pdf/1608.07905]
Multi-perspective context matching for machine comprehension
[https://arxiv.org/abs/1612.04211]
Reasonet: Learning to stop reading in machine comprehension
[http://dl.acm.org/citation.cfm?id=3098177]
Learning recurrent span representations for extractive question answering
[https://arxiv.org/abs/1611.01436]
End-to-end answer chunk extraction and ranking for reading comprehension
[https://arxiv.org/abs/1610.09996]
Words or characters? fine-grained gating for reading comprehension
[https://arxiv.org/abs/1611.01724]
Reading Wikipedia to Answer Open-Domain Questions
[https://arxiv.org/abs/1704.00051]
An analysis of prerequisite skills for reading comprehension
[http://www.aclweb.org/anthology/W/W16/W16-60.pdf#page=13]
A Comparative Study of Word Embeddings for Reading Comprehension
https://arxiv.org/pdf/1703.00993.pdf
Chen et al., 2017;Reading wikipedia to answer open- domain questions.
Huang et al., 2018;Flowqa: Grasping flow in history for conversational machine comprehension
Yu et al., 2018; Qanet: Combining local convolution with global self-attention for reading comprehen sion.
Zhipeng Chen, Yiming Cui, Wentao Ma, Shijin Wang, and Guoping Hu. 2019. Convolutional spatial attention model for reading comprehen- sion with multiple-choice questions.
Yiming Cui, Zhipeng Chen, Si Wei, Shijin Wang, Ting Liu, and Guoping Hu. 2017. Attention- over-attention neural networks for reading com- prehension.
Bhuwan Dhingra, Hanxiao Liu, Zhilin Yang, William Cohen, and Ruslan Salakhutdinov. 2017. Gated-attention readers for text com- prehension.
一些模型：
1 Memory Networks
1.1 Memory Network
1.2 End-To-End Memory Networks
1.3 Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
1.4 Key-Value Memory Networks for Directly Reading Documents
1.5 The Goldilocks Principle: Reading Children’s Books with Explicit Memory Representations
1.6 Can Active Memory Replace Attention?
2 DeepMind Attentive Reader
2.1 Teaching Machines to Read and Comprehend
3 Danqi’s Stanford Reader
3.1 [A thorough examination of the cnn/daily
4 Attention Sum Reader
5 Gated Attention Sum Reader
6 Attention Over Attention Reader
6.1 Attention-over-Attention Neural Networks for Reading Comprehension