【专知荟萃04】自动问答QA知识资料全集（入门/进阶/论文/代码/数据/综述/专家等）（附pdf下载）

点击上方“专知”关注获取更多AI知识!

【导读】主题荟萃知识是专知的核心功能之一，为用户提供AI领域系统性的知识学习服务。主题荟萃为用户提供全网关于该主题的精华（Awesome）知识资料收录整理，使得AI从业者便捷学习和解决工作问题！在专知人工智能主题知识树基础上，主题荟萃由专业人工编辑和算法工具辅助协作完成，并保持动态更新！另外欢迎对此创作主题荟萃感兴趣的同学，请加入我们专知AI创作者计划，共创共赢！ 今天专知为大家呈送第四篇专知主题荟萃-自动问答QA知识资料全集荟萃 （入门/进阶/论文/代码/数据/专家等），请大家查看！专知访问www.zhuanzhi.ai, 或关注微信公众号后台回复" 专知"进入专知，搜索主题“深度学习”查看。欢迎转发分享！此外，我们也提供该文pdf下载链接，请文章末尾查看！

了解专知，专知，一个新的认知方式！

• 自动问答 Question Answering 专知荟萃
  • 入门学习
  • 进阶文章
  • Tutorial
  • 综述
  • 视频教程
  • 代码
  • datasets
  • 领域专家

自动问答 Question Answering 专知荟萃

入门学习

1. 自动问答系统的类别 冯志伟
   • [http://blog.sina.com.cn/s/blog_72d083c70102du8m.html\]
2. 基于深度学习的智能问答 周小强 陈清财 曾华军
   • [https://yq.aliyun.com/articles/58745]
3. 基于知识图谱的电影自动问答系统（一）知识的获取与存储 (二）自动问答实现
   • [http://www.voidcn.com/article/p-hwhmeuje-ym.html]
   • [http://www.voidcn.com/article/p-wylzjird-ym.html]
4. 客服系统机器人产品设计详解——智能回答
   • [http://www.chanpin100.com/article/105410]
5. 聊天机器人与自动问答技术
   • [http://blog.csdn.net/heiyeshuwu/article/details/42965693]
6. 揭开知识库问答KB-QA的面纱
   • [https://zhuanlan.zhihu.com/p/25735572]
7. Question answering with TensorFlow
   • [https://www.oreilly.com/ideas/question-answering-with-tensorflow]

进阶文章

1. Towards AI-Complete Question Answering: A set of prerequisite toy tasks
   • [http://arxiv.org/pdf/1502.05698v10.pdf]
2. Large Scale simple question answering with Memory Networks - [https://arxiv.org/pdf/1506.02075v1.pdf]
3. Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
   • [http://arxiv.org/pdf/1506.07285v5.pdf]
4. Key-Value Memory Networks for directly understanding documents - [https://arxiv.org/pdf/1606.03126v1.pdf]
5. Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base
   • [https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/ACL15-STAGG.pdf]
6. Value of Semantic Parse Labeling for KBQA
   • [https://www.microsoft.com/en-us/research/wp-content/uploads/2016/08/acl2016-webqsp.pdf]
7. Question Answering with Subgraph Embeddings
   • [https://arxiv.org/pdf/1406.3676v3.pdf]
8. Open Question Answering with Weakly Supervised Embedding Models - [https://arxiv.org/pdf/1404.4326.pdf]
9. Learning End-to-End Goal-Oriented dialog
   • [https://arxiv.org/pdf/1605.07683v2.pdf]
10. End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding
    • [https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/IS16_ContextualSLU.pdf]
11. Question Answering over Knowledge Base With Neural Attention Combining Global Knowledge Information
    • [https://arxiv.org/pdf/1606.00979v1.pdf]
12. Compositional Learning of Embeddings for Relation Paths in Knowledge Bases and Texts
    • [https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/acl2016relationpaths-1.pdf]
13. Neural Machine Translation by jointly learning to align and translate - [https://arxiv.org/pdf/1409.0473v7.pdf]
14. Recurrent Neural Network Grammar
    • [https://arxiv.org/pdf/1602.07776v4.pdf]
15. Neural Turing Machines
    • [https://www.youtube.com/watch?v=_H0i0IhEO2g_)]
16. Teaching machines to read and comprehend
    • [https://arxiv.org/pdf/1506.03340.pdf]
17. Applying Deep Learning to answer selection: A study and an open task - [https://arxiv.org/pdf/1508.01585v2.pdf]
18. Reasoning with Neural Tensor Networks
    • [https://papers.nips.cc/paper/5028-reasoning-with-neural-tensor-networks-for-knowledge-base-completion.pdf]
19. Hybrid computing using a neural network with dynamic external memory
    • [http://www.nature.com/nature/journal/v538/n7626/full/nature20101.html)]
20. Gaussian Attention Model and its Application to Knowledge Base Embedding and Question Answering
    • [https://arxiv.org/pdf/1611.02266.pdf]
21. Gated Graph Sequence Neural Networks
    • [https://arxiv.org/abs/1511.05493]
22. Sequence to Sequence Learning With Neural Networks
    • [https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf]
23. Neural Conversation Model
    • [https://arxiv.org/pdf/1506.05869v1.pdf]
24. Query Reduction Networks For Question Answering
    • [https://arxiv.org/pdf/1606.04582.pdf]
25. Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
    • [https://arxiv.org/pdf/1606.01994.pdf]
26. Efficiently Answering Technical Questions — A Knowledge Graph Approach
    • [http://wangzhongyuan.com/en/papers/Technical_Questions_Answering.pdf]
27. An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge
    • [http://www.nlpr.ia.ac.cn/cip/~liukang/liukangPageFile/ACL2017-Hao.pdf]
28. Question Generation via Overgenerating Transformations and Ranking (Technical report)
    • [https://www.lti.cs.cmu.edu/sites/default/files/cmulti09013.pdf]
29. Automation of question generation from sentences
    • [http://www.sadidhasan.com/sadid-QG.pdf]
30. Good question!statistical ranking for question generation
    • [https://homes.cs.washington.edu/~nasmith/papers/heilman+smith.naacl10.pdf]
31. Question generation from paragraphs at upenn: Qgstec system description
    • [http://www.aclweb.org/anthology/I11-1104]
32. Automatically generating questions from queries for community-based question answering
    • [http://www.aclweb.org/anthology/I11-1104]
33. How to Generate Cloze Questions from Definitions: A Syntactic Approach - [https://www.cs.cmu.edu/~listen/pdfs/gates-2011-aaai-qg.pdf]
34. Generating natural language questions to support learning on-line - [http://www.aclweb.org/anthology/W13-2114]
35. Deep questions without deep understanding - [http://www.aclweb.org/anthology/P15-1086]
36. Semi-supervised qa with generative domain-adaptive nets
    • [https://pdfs.semanticscholar.org/e8a0/536dc080acd2ca83502dddd0d511ef3fbd8c.pdf]
37. Leveraging multiple views of text for automatic question generation
    • [http://link.springer.com/chapter/10.1007/978-3-319-19773-9_26]
38. Revup: Automatic gap-fill question generation from educational texts
    • [http://www.aclweb.org/anthology/W15-0618]
39. Towards topic-to-question generatio
    • [http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00206]
40. Ranking automatically generated questions using common human queries
    • [http://www.aclweb.org/old_anthology/W/W16/W16-66.pdf#page=233]
41. Generating quiz questions from knowledge graphs
    • [https://dl.acm.org/citation.cfm?doid=2740908.2742722]
42. Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
    • [http://arxiv.org/pdf/1603.06807v1.pdf]
43. Knowledge Questions from Knowledge Graphs
    • [https://arxiv.org/abs/1610.09935]
44. Machine Comprehension by Text-to-Text Neural Question Generation - [http://aclweb.org/anthology/W17-2603]
45. Question Generation from a Knowledge Base with Web Exploration - [https://arxiv.org/pdf/1610.03807.pdf]
46. On Generating Characteristic-rich Question Sets for QA Evaluation - [http://www.aclweb.org/anthology/D/D16/D16-1054.pdf]
47. Neural Question Generation from Text: A Preliminary Study
    • [https://arxiv.org/pdf/1704.01792.pdf]

Tutorial

1. Question Answering Become Main Theme of IR Research? 李航 今日头条
   • [http://www.hangli-hl.com/uploads/3/4/4/6/34465961/airs_2016_question_answering.pdf\]
   • [http://lab.toutiao.com/index.php/2017/03/02/huaweilihangwill-question-answering-become-main-theme-of-research-in-information-retrieval.html]
2. 深度问答技术 中科院自动化所 赵军老师
   • [链接：http://pan.baidu.com/s/1qYJV1Ti 密码：99c4]
3. 深度学习与智能问答 CCL 2016 Tutorial 刘康 冯岩松
   1. 基于传统符号表示的知识库问答
   2. 基于深度学习的知识库问答
   3. 基于深度学习的对话系统
   4. 基于深度学习的阅读 解
   5. [https://pan.baidu.com/s/1bpDAf8r]
   6. [http://www.cips-cl.org/static/CCL2016/tutorialsT2B.html]
4. 基于知识的智能问答技术 冯岩松 2017. [http://cips-upload.bj.bcebos.com/2017/ssatt2017/ATT2017-QAI.pdf]
5. 自动问答、聊天机器人与自然语言理解 中国计算机学会《学科前沿讲习班》 by 严睿 段楠 段楠 熊德意 高剑峰 谢幸 http://tcci.ccf.org.cn/conference/2017/adlnotice.php

综述

1. 《Speeh and Language Processing》Chapter 28 Question Answering
   • [https://web.stanford.edu/~jurafsky/slp3/28.pdf\]
2. A Survey of Text Question Answering Techniques. Poonam Gupta,Vishal Gupta
   • [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.258.7801&rep=rep1&type=pdf]
3. Question Answering Systems: Survey and Trends
   • [http://www.sciencedirect.com/science/article/pii/S1877050915034663]
4. The Question Answering Systems: A Survey
   • [https://www.researchgate.net/publication/311425566_The_Question_Answering_Systems_A_Survey\]
5. 面向知识自动化的自动问答研究进展 [http://www.aas.net.cn/CN/10.16383/j.aas.2017.c160667]
6. 自动问答综述 2002年 by 郑实福,刘挺,秦兵,李生 [http://jcip.cipsc.org.cn/CN/abstract/abstract1282.shtml]
7. 基于 Web 的问答系统综述 2017 李舟军李水华 [http://www.jsjkx.com/jsjkx/ch/reader/create_pdf.aspx?file_no=20170601&flag=&journal_id=jsjkx&year_id=2017\]

视频教程

1. 深度学习在自动问答系统中的应用 李成华
   • [http://www.infoq.com/cn/presentations/deep-learing-on-automatic-question-answering-system]

代码

1. MemNN Impl Matlab
   • [https://github.com/facebook/MemNN]
2. Key Value MemNN
   • [https://github.com/siyuanzhao/key-value-memory-networks]
3. Quepy
   • [https://github.com/machinalis/quepy]
4. NLQuery
   • [https://github.com/ayoungprogrammer/nlquery]
5. ParlAI
   • [https://github.com/facebookresearch/ParlAI]
6. flask-chatterbot
   • [https://github.com/chamkank/flask-chatterbot]
7. Learning to Rank short text pairs with CNN SIGIR 2015
   • [https://github.com/shashankg7/Keras-CNN-QA]
8. TextKBQA
   • [https://github.com/rajarshd/TextKBQA]
9. BiAttnFlow
   • [https://github.com/allenai/bi-att-flow]

Datasets

1. SQuAD The Stanford Question Answering Dataset
   • [https://rajpurkar.github.io/SQuAD-explorer/]
2. CNN QA Task (Teaching Machines to Read & Comprehend)
   • [https://github.com/deepmind/rc-data/]
3. WebQuestions
   • [http://nlp.stanford.edu/software/sempre/]
4. Simple Questions
   • [https://research.facebook.com/research/babi]
5. Movie QA
   • [https://research.facebook.com/research/babi/]
6. WebQuestionsSP
   • [https://www.microsoft.com/en-us/download/details.aspx?id=52763]
7. WikiQA
   • [https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/YangYihMeek_EMNLP-15_WikiQA.pdf]
8. Kaggle AllenAI Challenge
   • [https://www.kaggle.com/c/the-allen-ai-science-challenge]
9. MC Test, Machine Comprehension Test Microsoft 2013
   • [http://research.microsoft.com/en-us/um/redmond/projects/mctest/]
10. MSR Sentence Completion Challenge
    • [https://www.microsoft.com/en-us/research/project/msr-sentence-completion-challenge/]
11. Dialog State Tracking Challenge
    • [http://camdial.org/~mh521/dstc/]
12. QA dataset featured in Teaching Machines to Read and Comprehend
    • [https://github.com/deepmind/rc-data/]
13. WebNav
    • [https://github.com/nyu-dl/WebNav/blob/master/README.md]
14. Stanford Question Answering Dataset
    • [https://rajpurkar.github.io/SQuAD-explorer/]
15. FB15K Knowledge Base
    • [https://www.microsoft.com/en-us/download/details.aspx?id=52312]
16. WikiQA
    • [http://aka.ms/WikiQA)]
17. Quora Duplicate Questions Dataset
    • [https://data.quora.com/)]
18. Query Reformulator Dataset Jeopardy etc
    • [https://github.com/nyu-dl/QueryReformulator)]
19. Quiz Bowl Questions
    • [https://www.cs.colorado.edu/~jbg/projects/IIS-1320538.html#Datasets]
20. WebQA-Chinese
    • [http://idl.baidu.com/WebQA.html]
21. Chat corpus
    • [https://github.com/Marsan-Ma/chat_corpus]
22. DeepMind Q&A Dataset - [http://cs.nyu.edu/~kcho/DMQA/]
23. WebQuestions - [https://worksheets.codalab.org/worksheets/0xba659fe363cb46e7a505c5b6a774dc8a/#]
24. WebQA
    • http://idl.baidu.com/WebQA.html
25. GraphQuestions
    • https://github.com/ysu1989/GraphQuestions

领域专家

1. 刘康博士，中科院自动化所模式识别国家重点实验室副研究员，中国中文信息学会青年工作委员会执行委员。研究领域包括信息抽取、网络挖掘、问答系统等，同时也涉及模式识别与机器学习方面的基础研究。在自然语言处理、知识工程等领域国际重要会议和期刊发表论文三十余篇（如TKDE、ACL、IJCAI、EMNLP、COLING、CIKM等），曾获KDD CUP 2011 Track2 全球亚军，COLING 2014最佳论文奖，首届“CCF-腾讯犀牛鸟基金卓越奖”、2014年度中国中文信息学会“钱伟长中文信息处理科学技术奖-汉王青年创新一等奖”、2015 Google Focused Research Award等。 - 个人主页：http://www.nlpr.ia.ac.cn/cip/~liukang/index.html
2. 冯岩松博士，北京大学计算机科学与技术研究所讲师。2011年毕业于英国爱丁堡大学，获得信息科学博士学位。主要研究方向包括自然语言处理、信息抽取以及机器学习在自然语言处理中的应用；已连续三年在面向结构化知识库的知识问答评测QALD-4, 5, 6中获得第一名；相关工作已发表在TPAMI、ACL、EMNLP等主流期刊与会议上。同时，作为项目负责人或课题骨干已承担多项国家自然科学基金及科技部863计划项目。分别在 2014 和 2015 年获得 IBM Faculty Award。 - 个人主页：https://sites.google.com/site/ysfeng/home
3. 严睿，北京大学研究员，前百度公司资深研发，华中师范大学与中央财经大学客座教授与校外导师。主持研发多个开放领域对话系统和服务类对话系统，发表高水平研究论文近50篇，担任多个学术会议（KDD, SIGIR, ACL, WWW, AAAI, CIKM, EMNLP等）的（高级）程序委员会委员及审稿人。
   • [http://59.108.48.5/wip/team/teacher/zh/yanrui]
4. 段楠博士，微软亚洲研究院自然语言计算组主管研究员，长期从事自动问答、对话系统、语义理解、文本生成和网络搜索等自然语言处理研究。段楠博士的多项研究成果已经转化到微软重要人工智能产品中，例如必应搜索、微软小冰、Cortana语音助手等。自2015年起，段楠博士开始担任NLPCC开放领域中文自动问答评测的负责人。 [https://www.microsoft.com/en-us/research/people/nanduan/]
5. 高剑峰是微软合伙人，微软Redmond总部人工智能部门的研究经理（Partner Research Manager）。他致力于深度学习在文本和图像处理方面的研发，领导机器阅读理解、问答、对话方面的研究和人工智能系统开发，以及微软新一代商务人工智能系统的研发。6. 谢幸博士于2001年7月加入微软亚洲研究院，现任社会计算组高级主任研究员，并任中国科技大学兼职博士生导师。他分别于1996年和2001年在中国科技大学获得计算机软件专业学士和博士学位。目前，他的团队在数据挖掘、社会计算和普适计算等领域展开创新性的研究。 [https://www.microsoft.com/en-us/research/people/jfgao/]
6. 谢幸，微软亚洲研究院，任社会计算组高级主任研究员，并任中国科技大学兼职博士生导师。目前，他的团队在数据挖掘、社会计算和普适计算等领域展开创新性的研究。他是ACM、IEEE高级会员和计算机学会杰出会员，多次担任顶级国际会议程序委员会委员和领域主席等职位。 [https://www.microsoft.com/en-us/research/people/xingx/]
7. Percy Liang 斯坦福大学计算机系助理教授、斯坦福人工智能实验室成员 [https://cs.stanford.edu/~pliang/\]
8. 赵军 博导 中国科学院自动化研究所 http://people.ucas.ac.cn/~zhaojun
9. 黄民烈 清华大学http://www.tsinghua.edu.cn/publish/cs/4616/2013/20131122151220708543803/20131122151220708543803_.html

汇总不全面，欢迎补全和提建议，敬请关注http://www.zhuanzhi.ai 和关注专知公众号，获取第一手AI相关知识