{"id":13704246,"url":"https://github.com/teacherpeterpan/Question-Generation-Paper-List","last_synced_at":"2025-05-05T09:33:32.953Z","repository":{"id":45720217,"uuid":"228843809","full_name":"teacherpeterpan/Question-Generation-Paper-List","owner":"teacherpeterpan","description":"A summary of must-read papers for Neural Question Generation (NQG)","archived":false,"fork":false,"pushed_at":"2021-10-25T12:52:49.000Z","size":70,"stargazers_count":583,"open_issues_count":2,"forks_count":79,"subscribers_count":28,"default_branch":"master","last_synced_at":"2024-08-03T21:04:50.046Z","etag":null,"topics":["paper-list","question-generation"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/teacherpeterpan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-12-18T13:16:13.000Z","updated_at":"2024-07-30T07:49:09.000Z","dependencies_parsed_at":"2022-07-21T22:33:44.578Z","dependency_job_id":null,"html_url":"https://github.com/teacherpeterpan/Question-Generation-Paper-List","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/teacherpeterpan%2FQuestion-Generation-Paper-List","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/teacherpeterpan%2FQuestion-Generation-Paper-List/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/teacherpeterpan%2FQuestion-Generation-Paper-List/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/teacherpeterpan%2FQuestion-Generation-Paper-List/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/teacherpeterpan","download_url":"https://codeload.github.com/teacherpeterpan/Question-Generation-Paper-List/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224439840,"owners_count":17311536,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["paper-list","question-generation"],"created_at":"2024-08-02T21:01:06.264Z","updated_at":"2024-11-13T11:31:05.880Z","avatar_url":"https://github.com/teacherpeterpan.png","language":null,"funding_links":[],"categories":["NLP"],"sub_categories":[],"readme":"# Question-Generation-Paper-List\nA summary of must-read papers for Neural Question Generation (NQG)\n\n- Contributed by **[Liangming Pan](http://www.liangmingpan.com)**, **[Yuxi Xie](https://yuxixie.github.io/)** and **[Yunxiang Zhang](https://github.com/yunx-z)**\n\nPlease follow [this link](./README_by_year.md) to view papers in chronological order. \n\n## [Content](#content)\n\n\u003ctable\u003e\n\u003ctr\u003e\u003ctd colspan=\"2\"\u003e\u003ca href=\"#survey-papers\"\u003e1. Survey\u003c/a\u003e\u003c/td\u003e\u003c/tr\u003e \n\u003ctr\u003e\u003ctd colspan=\"2\"\u003e\u003ca href=\"#models\"\u003e2. Models\u003c/a\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#basic-seq2seq-models\"\u003e2.1 Basic Seq2Seq Models\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#encoding-answers\"\u003e2.2 Encoding Answers\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#linguistic-features\"\u003e2.3 Linguistic Features\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#question-specific-rewards\"\u003e2.4 Question-specific Rewards\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#content-selection\"\u003e2.5 Content Selection\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#question-type-modeling\"\u003e2.6 Question Type Modeling\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#encode-wider-contexts\"\u003e2.7 Encode wider contexts\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#qg-with-pretraining\"\u003e2.8 QG with pretraining\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#other-directions\"\u003e2.9 Other Directions\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\u003ctd colspan=\"2\"\u003e\u003ca href=\"#applications\"\u003e2. Applications\u003c/a\u003e\u003c/td\u003e\u003c/tr\u003e \n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#difficulty-controllable-QG\"\u003e2.1 Difficulty Controllable QG\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#conversational-QG\"\u003e2.2 Conversational QG\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e \n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#asking-deep-questions\"\u003e2.3 Asking Deep Questions\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#combining-QA-and-QG\"\u003e2.4 Combining QA and QG\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#QG-from-knowledge-graphs\"\u003e2.5 QG from knowledge graphs\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#visual-question-generation\"\u003e2.6 Visual Question Generation\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e \n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#distractor-generation\"\u003e2.7 Distractor Generation\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u0026ensp;\u003ca href=\"#cross-lingual-QG\"\u003e2.8 Cross-lingual QG\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n    \u003ctd\u003e\u0026emsp;\u003ca href=\"#clarification-question-generation\"\u003e2.9 Clarification Question Generation\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\u003ctd colspan=\"2\"\u003e\u003ca href=\"#evaluation\"\u003e3. Evaluation\u003c/a\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd colspan=\"2\"\u003e\u003ca href=\"#resources\"\u003e4. Resources\u003c/a\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003c/table\u003e\n\n## [Survey papers](#content)\n1. **Recent Advances in Neural Question Generation.** arxiv, 2019. [paper](https://arxiv.org/pdf/1905.08949.pdf)\n    \n    *Liangming Pan, Wenqiang Lei, Tat-Seng Chua, Min-Yen Kan* \n\n2. **A Systematic Review of Automatic Question Generation for Educational Purposes.** International Journal of Artificial Intelligence in Education, 2020. [paper](https://link.springer.com/content/pdf/10.1007/s40593-019-00186-y.pdf)\n    \n    *Ghader Kurdi, Jared Leo, Bijan Parsia, Uli Sattler, Salam Al-Emari* \n\n3. **A Review on Question Generation from Natural Language Text.** ACM Transactions on Information Systems, Volume 40, Issue 1, 2022. [paper](https://dl.acm.org/doi/pdf/10.1145/3468889)\n\n    *Ruqing Zhang, Jiafeng Guo, Lu Chen, Yixing Fan, Xueqi Cheng*\n\n## [Models](#content)   \n\n### [Basic Seq2Seq Models](#basic-models)\n\nBasic Seq2Seq models with attention to generate questions. \n\n1. **Learning to ask: Neural question generation for reading comprehension.** ACL, 2017. [paper](https://www.aclweb.org/anthology/P17-1123.pdf)\n\n    *Xinya Du, Junru Shao, Claire Cardie.*\n\n2. **Neural question generation from text: A preliminary study.** NLPCC, 2017. [paper](https://www.researchgate.net/profile/Franco_Scarselli/publication/4202380_A_new_model_for_earning_in_raph_domains/links/0c9605188cd580504f000000.pdf)\n\n    *Qingyu Zhou, Nan Yang, Furu Wei, Chuanqi Tan, Hangbo Bao, Ming Zhou.*\n\n3. **Machine comprehension by text-to-text neural question generation.** Rep4NLP@ACL, 2017. [paper](https://arxiv.org/pdf/1705.02012.pdf)\n   \n   *Xingdi Yuan, Tong Wang, Çaglar Gülçehre, Alessandro Sordoni, Philip Bachman, Saizheng Zhang, Sandeep Subramanian, Adam Trischler*\n\n### [Encoding Answers](#answer-encoding)\n\nApplying various techniques to encode the answer information thus allowing for better quality answer-focused questions. \n\n1. **Answer-focused and Position-aware Neural Question Generation.** EMNLP, 2018. [paper](https://www.aclweb.org/anthology/D18-1427)\n   \n   *Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang*\n\n2. **Improving Neural Question Generation Using Answer Separation.** AAAI, 2019. [paper](https://arxiv.org/pdf/1809.02393.pdf) [code](https://github.com/yanghoonkim/NQG_ASs2s)\n\n    *Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung.*\n\n3. **Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring.** AAAI, 2020. [paper](https://arxiv.org/pdf/1912.00879.pdf)\n   \n   *Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Wu*\n\n4. **Answer-driven Deep Question Generation based on Reinforcement Learning.** COLING, 2020. [paper](https://www.aclweb.org/anthology/2020.coling-main.452/)\n\n   *Liuyin Wang, Zihan Xu, Zibo Lin, Hai-Tao Zheng, Ying Shen*\n\n### [Linguistic Features](#linguistic-features)\n\nImprove QG by incorporating various linguistic features into the QG process. \n\n1. **Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features.** INLG, 2018. [paper](https://arxiv.org/pdf/1809.02637.pdf)\n\n    *Vrindavan Harrison, Marilyn Walker*\n\n2. **Automatic Question Generation using Relative Pronouns and Adverbs.** ACL, 2018. [paper](https://www.aclweb.org/anthology/P18-3022)\n   \n   *Payal Khullar, Konigari Rachna, Mukul Hase, Manish Shrivastava* \n\n3. **Learning to Generate Questions by Learning What not to Generate.** WWW, 2019. [paper](https://arxiv.org/pdf/1902.10418.pdf) [code](https://github.com/BangLiu/QG)\n\n    *Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu.*\n\n4. **Improving Neural Question Generation using World Knowledge.** arXiv, 2019. [paper](https://arxiv.org/pdf/1909.03716.pdf)\n   \n   *Deepak Gupta, Kaheer Suleman, Mahmoud Adada, Andrew McNamara, Justin Harris*\n\n5. **Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation.** ACL, 2020. [paper](https://arxiv.org/pdf/2004.08694.pdf)\n   \n   *Kaustubh D. Dhole, Christopher D. Manning*\n\n6. **Automatically Generating Cause-and-Effect Questions from Passages.** EACL Workshop, 2021. [paper](https://www.aclweb.org/anthology/2021.bea-1.17.pdf) [codes](https://github.com/kstats/CausalQG)\n    \n    *Katherine Stasaski, Manav Rathod, Tony Tu, Yunfang Xiao, Marti A. Hearst*\n\n7. **Asking It All: Generating Contextualized Questions for any Semantic Role.** EMNLP, 2021. [paper](https://arxiv.org/pdf/2109.04832) [codes](https://github.com/ValentinaPy/RoleQGeneration)\n\n    *Valentina Pyatkin, Paul Roit, Julian Michael, Yoav Goldberg, Reut Tsarfaty and Ido Dagan*\n\n### [Question-specific Rewards](#RL-rewards)\n\nImproving the training via combining supervised and reinforcement learning to maximize question-specific rewards\n\n1. **Teaching Machines to Ask Questions.** IJCAI, 2018. [paper](https://www.ijcai.org/proceedings/2018/0632.pdf)\n   \n   *Kaichun Yao, Libo Zhang, Tiejian Luo, Lili Tao, Yanjun Wu*\n\n2. **Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model** NeurIPS Workshop, 2019. [paper](https://arxiv.org/pdf/1910.08832.pdf)\n   \n   *Yu Chen, Lingfei Wu, Mohammed J. Zaki*\n\n3. **Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text** CoNLL, 2019. [paper](https://arxiv.org/pdf/1808.04961.pdf)\n   \n   *Vishwajeet Kumar, Ganesh Ramakrishnan, Yuan-Fang Li*\n\n4. **Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering** EMNLP, 2019. [paper](https://arxiv.org/pdf/1909.06356.pdf) [code](https://github.com/ZhangShiyue/QGforQA)\n   \n   *Shiyue Zhang, Mohit Bansal*\n\n5. **Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation** ICLR, 2020. [paper](https://arxiv.org/pdf/1908.04942.pdf) [codes](https://github.com/hugochan/RL-based-Graph2Seq-for-NQG)\n   \n   *Yu Chen, Lingfei Wu, Mohammed J. Zaki*\n\n12. **Exploring Question-Specific Rewards for Generating Deep Questions.** COLING, 2020. [paper](https://arxiv.org/pdf/2011.01102.pdf) [codes](https://github.com/YuxiXie/RL-for-Question-Generation)\n    \n    *Yuxi Xie, Liangming Pan, Dongzhe Wang, Min-Yen Kan, Yansong Feng*\n\n13. **Answer-driven Deep Question Generation based on Reinforcement Learning.** COLING, 2020. [paper](https://www.aclweb.org/anthology/2020.coling-main.452/)\n\n    *Liuyin Wang, Zihan Xu, Zibo Lin, Hai-Tao Zheng, Ying Shen*\n\n7. **Cooperative Learning of Zero-Shot Machine Reading Comprehension.** arXiv, 2021. [paper](https://arxiv.org/pdf/2103.07449)\n    \n    *Hongyin Luo, Shang-Wen Li, Seunghak Yu, James Glass*\n\n7. **Contrastive Multi-document Question Generation.** EACL, 2021. [paper](https://www.aclweb.org/anthology/2021.eacl-main.2.pdf) [codes](https://github.com/woonsangcho/contrast_qgen)\n    \n    *Woon Sang Cho, Yizhe Zhang, Sudha Rao, Asli Celikyilmaz, Chenyan Xiong, Jianfeng Gao, Mengdi Wang, Bill Dolan*\n\n7. **Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning.** EMNLP, 2021. [paper](https://arxiv.org/pdf/2109.04689) [codes](https://github.com/amazon-research/SC2QA-DRIL)\n\n    *Li Zhou, Kevin Small, Yong Zhang and Sandeep Atluri*\n\n### [Content Selection](#content-selection)\n\nImprove QG by considering how to select question-worthy contents (content selection) before asking a question. \n\n1. **Identifying Where to Focus in Reading Comprehension for Neural Question Generation.** EMNLP, 2017. [paper](https://www.aclweb.org/anthology/D17-1219.pdf)\n   \n   *Xinya Du, Claire Cardie*\n\n2. **Neural Models for Key Phrase Extraction and Question Generation.** ACL Workshop, 2018. [paper](https://www.aclweb.org/anthology/W18-2609.pdf)\n   \n   *Sandeep Subramanian, Tong Wang, Xingdi Yuan, Saizheng Zhang, Adam Trischler, Yoshua Bengio*\n\n3. **A Comparative Study on Question-Worthy Sentence Selection Strategies for Educational Question Generation.** AIED, 2019. [paper](https://link.springer.com/chapter/10.1007/978-3-030-23204-7_6)\n   \n   *Guanliang Chen, Jie Yang, Dragan Gasevic*\n\n4. **Learning to Generate Questions by Learning What not to Generate.** WWW, 2019. [paper](https://arxiv.org/pdf/1902.10418.pdf) [code](https://github.com/BangLiu/QG)\n\n    *Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu.*\n\n5. **Improving Question Generation With to the Point Context.** EMNLP, 2019. [paper](https://arxiv.org/pdf/1910.06036.pdf)\n\n    *Jingjing Li, Yifan Gao, Lidong Bing, Irwin King, Michael R. Lyu.*\n\n6. **Weak Supervision Enhanced Generative Network for Question Generation.** IJCAI, 2019. [paper](https://arxiv.org/pdf/1907.00607v1)\n   \n   *Yutong Wang, Jiyuan Zheng, Qijiong Liu, Zhou Zhao, Jun Xiao, Yueting Zhuang*\n\n7. **A Multi-Agent Communication Framework for Question-Worthy Phrase Extraction and Question Generation.** AAAI, 2019. [paper](https://www.aaai.org/ojs/index.php/AAAI/article/view/4700/4578)\n   \n   *Siyuan Wang, Zhongyu Wei, Zhihao Fan, Yang Liu, Xuanjing Huang*\n\n8. **Self-Attention Architectures for Answer-Agnostic Neural Question Generation.** ACL, 2019. [paper](https://www.aclweb.org/anthology/P19-1604.pdf)\n   \n   *Thomas Scialom, Benjamin Piwowarski, Jacopo Staiano.*\n\n9. **Mixture Content Selection for Diverse Sequence Generation.** EMNLP, 2019. [paper](https://arxiv.org/pdf/1909.01953.pdf) [code](https://github.com/clovaai/FocusSeq2Seq)\n   \n   *Jaemin Cho, Minjoon Seo, Hannaneh Hajishirzi*\n\n10. **Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus.** WWW, 2020. [paper](https://arxiv.org/pdf/2002.00748.pdf)\n    \n    *Bang Liu, Haojie Wei, Di Niu, Haolan Chen, Yancheng He*\n\n### [Question Type Modeling](#question-type-modeling)\n\nImprove QG by explicitly modeling question types or interrogative words. \n\n1. **Question Generation for Question Answering.** EMNLP,2017. [paper](https://www.aclweb.org/anthology/D17-1090)\n   \n   *Nan Duan, Duyu Tang, Peng Chen, Ming Zhou*\n\n2. **Answer-focused and Position-aware Neural Question Generation.** EMNLP, 2018. [paper](https://www.aclweb.org/anthology/D18-1427)\n   \n   *Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang*\n\n3. **Let Me Know What to Ask: Interrogative-Word-Aware Question Generation** EMNLP Workshop, 2019. [paper](https://arxiv.org/pdf/1910.13794.pdf)\n   \n   *Junmo Kang, Haritz Puerto San Roman, Sung-Hyon Myaeng*\n\n4. **Question-type Driven Question Generation** EMNLP, 2019. [paper](https://arxiv.org/pdf/1909.00140.pdf)\n   \n   *Wenjie Zhou, Minghua Zhang, Yunfang Wu*\n\n5. **Expanding, Retrieving and Infilling: Diversifying Cross-Domain Question Generation with Flexible Templates.** EACL, 2021. [paper](https://www.aclweb.org/anthology/2021.eacl-main.279.pdf) [codes](https://github.com/xiaojingyu92/ERIQG)\n    \n    *Xiaojing Yu, Anxiao Jiang*\n\n### [Encode Wider Contexts](#encode-wider-contexts)\n\nImprove QG by incorporating wider contexts in the input passage. \n\n1. **Harvesting paragraph-level question-answer pairs from wikipedia.** ACL, 2018. [paper](https://arxiv.org/pdf/1805.05942.pdf) [code\u0026dataset](https://github.com/xinyadu/HarvestingQA)\n    \n    *Xinya Du, Claire Cardie*\n\n2. **Leveraging Context Information for Natural Question Generation** ACL, 2018. [paper](https://www.aclweb.org/anthology/N18-2090) [code](https://github.com/freesunshine0316/MPQG)\n   \n   *Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea*\n\n3. **Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks.** EMNLP, 2018. [paper](https://www.aclweb.org/anthology/D18-1424.pdf)\n   \n   *Yao Zhao, Xiaochuan Ni, Yuanyuan Ding, Qifa Ke*\n\n4. **Capturing Greater Context for Question Generation** AAAI, 2020. [paper](https://arxiv.org/pdf/1910.10274.pdf)\n   \n   *Luu Anh Tuan, Darsh J Shah, Regina Barzilay*\n\n5. **How to Ask Good Questions? Try to Leverage Paraphrases** ACL, 2020. [paper](https://www.aclweb.org/anthology/2020.acl-main.545.pdf)\n   \n   *Xin Jia, Wenjie Zhou, Xu SUN, Yunfang Wu*\n\n6. **PathQG: Neural Question Generation from Facts** EMNLP, 2020. [paper](http://www.sdspeople.fudan.edu.cn/zywei/paper/2020/wangsy-emnlp-2020.pdf) [code](https://github.com/WangsyGit/PathQG)\n   \n   *Siyuan Wang, Zhongyu Wei, Zhihao Fan, Zengfeng Huang, Weijian Sun, Qi Zhang, Xuanjing Huang*\n\n7. **AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents.** EACL Demo, 2021. [paper](https://arxiv.org/pdf/2103.03820.pdf) [codes](https://github.com/roemmele/answerquest)\n    \n    *Melissa Roemmele, Deep Sidhpura, Steve DeNeefe, Ling Tsou*\n\n8. **OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach.** arXiv, 2021. [paper](https://arxiv.org/pdf/2102.12128)\n    \n    *Shaobo Cui, Xintong Bao, Xinxing Zu, Yangyang Guo, Zhongzhou Zhao, Ji Zhang, Haiqing Chen*\n\n9. **ASQ: Automatically Generating Question-Answer Pairs using AMRs.** arXiv, 2021. [paper](https://arxiv.org/pdf/2105.10023)\n    \n    *Geetanjali Rakshit, Jeffrey Flanigan*\n\n10. **Zero-shot Fact Verification by Claim Generation.** ACL, 2021. [paper](https://arxiv.org/pdf/2105.14682) [codes](https://github.com/teacherpeterpan/Zero-shot-Fact-Verification)\n    \n    *Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang*\n\n11. **Iterative GNN-based Decoder for Question Generation.** EMNLP, 2021. [paper](http://qizhang.info/paper/emnlp2021.3921_Paper.pdf)\n\n    *Zichu Fei, Qi Zhang and Yaqian Zhou*\n\n### [QG with pretraining](#qg-with-pretraining)\n\nImprove QG ultilizing NLP pretraining models. \n\n1. **Unified Language Model Pre-training for Natural Language Understanding and Generation.** NeurIPS, 2019. [paper](https://arxiv.org/pdf/1905.03197.pdf) [code](https://github.com/microsoft/unilm)\n   \n   *Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon*\n\n2. **A Recurrent BERT-based Model for Question Generation.** MRQA Workshop, 2019. [paper](https://www.aclweb.org/anthology/D19-5821.pdf)\n\n   *Ying-Hong Chan, Yao-Chung Fan*\n\n3. **CopyBERT: A Unified Approach to Question Generation with Self-Attention.** ACL Workshop, 2020. [paper](https://www.aclweb.org/anthology/2020.nlp4convai-1.3.pdf) [code](https://github.com/StalVars/CopyBERT)\n\n   *Stalin Varanasi, Saadullah Amin, Guenter Neumann*\n\n4. **QURIOUS: Question Generation Pretraining for Text Generation.** arXiv, 2020. [paper](https://arxiv.org/pdf/2004.11026.pdf)\n   \n   *Shashi Narayan, Gonçalo Simoes, Ji Ma, Hannah Craighead, Ryan Mcdonald*\n\n5. **UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training.** arXiv, 2020. [paper](https://arxiv.org/pdf/2002.12804.pdf) [code](https://github.com/microsoft/unilm/tree/master/unilm)\n   \n   *Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Songhao Piao, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon*\n\n### [Other Directions](#other-model)\n\n1. **Generating Question-Answer Hierarchies.** ACL, 2019. [paper](https://arxiv.org/pdf/1906.02622.pdf) [code](http://squash.cs.umass.edu/)\n   \n   *Kalpesh Krishna and Mohit Iyyer.*\n\n2. **Can You Unpack That? Learning to Rewrite Questions-in-Context.** EMNLP, 2019. [paper](https://www.aclweb.org/anthology/D19-1605.pdf)\n   \n   *Ahmed Elgohary, Denis Peskov, Jordan L. Boyd-Graber*\n\n3. **Sequential Copying Networks.** AAAI, 2018. [paper](https://arxiv.org/pdf/1807.02301.pdf)\n   \n   *Qingyu Zhou, Nan Yang, Furu Wei, Ming Zhou*\n\n4. **Let's Ask Again: Refine Network for Automatic Question Generation.** EMNLP, 2019. [paper](https://www.aclweb.org/anthology/D19-1326.pdf)\n   \n   *Preksha Nema, Akash Kumar Mohankumar, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran*\n\n## [Applications](#applications)\n\n### [Difficulty Controllable QG](#difficulty-controllable-QG)\n\nEndowing the model with the ability to control the difficulty of the generated questions. \n\n1. **Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation.** arxiv, 2019. [paper](https://arxiv.org/pdf/1912.02367.pdf)\n\n    *Jie Zhao, Xiang Deng, Huan Sun.*\n\n2. **Difficulty Controllable Generation of Reading Comprehension Questions.** IJCAI, 2019. [paper](https://www.ijcai.org/proceedings/2019/0690.pdf)\n   \n   *Yifan Gao, Lidong Bing, Wang Chen, Michael R. Lyu, Irwin King* \n\n3. **Difficulty-controllable Multi-hop Question Generation From Knowledge Graphs.** ISWC, 2019. [paper](https://arxiv.org/pdf/1807.03586.pdf)  [code\u0026dataset](https://github.com/liyuanfang/mhqg)\n   \n   *Vishwajeet Kumar, Yuncheng Hua, Ganesh Ramakrishnan, Guilin Qi, Lianli Gao, Yuan-Fang Li*\n\n4. **Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting.** ACL, 2021. [paper](https://arxiv.org/pdf/2105.11698) [codes](https://tinyurl.com/19esunzz)\n    \n    *Yi Cheng, Siyao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, Yefeng Zheng*\n\n7. **Question Generation for Adaptive Education.** ACL, 2021. [paper](https://arxiv.org/abs/2106.04262) [codes](https://github.com/meghabyte/acl2021-education)\n    \n    *Megha Srivastava, Noah Goodman*\n\n### [Conversational QG](#conversational-QG)\n\nLearning to generate a series of coherent questions grounded in a question answering style conversation. \n\n1. **Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders.** ACL, 2018. [paper](https://arxiv.org/pdf/1805.04843.pdf) [code](https://github.com/victorywys/Learning2Ask_TypedDecoder) [dataset]( http://coai.cs.tsinghua.edu.cn/hml/dataset/)\n   \n   *Yansen Wang, Chenyi Liu, Minlie Huang, Liqiang Nie*\n\n2. **Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog.** NIPS, 2018. [paper](https://arxiv.org/pdf/1802.03881.pdf)\n\n   *Sang-Woo Lee, Yu-Jung Heo, Byoung-Tak Zhang*\n\n3. **Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling.** ACL, 2019. [paper](https://arxiv.org/pdf/1906.06893.pdf) [code](https://github.com/Evan-Gao/conversational-QG)\n   \n   *Yifan Gao, Piji Li, Irwin King, Michael R. Lyu*\n\n4. **Reinforced Dynamic Reasoning for Conversational Question Generation.** ACL, 2019. [paper](https://www.aclweb.org/anthology/P19-1203) [code](https://github.com/ZJULearning/ReDR) [dataset](https://stanfordnlp.github.io/coqa/)\n   \n   *Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun*\n\n5. **Towards Answer-unaware Conversational Question Generation.** ACL Workshop, 2019. [paper](https://www.aclweb.org/anthology/D19-5809.pdf)\n   \n   *Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi*\n\n6. **What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog.** ACL, 2019. [paper](https://www.aclweb.org/anthology/P19-1646.pdf)\n   \n   *Pushkar Shukla, Carlos Elmadjian, Richika Sharan, Vivek Kulkarni, Matthew Turk, William Yang Wang*\n\n7. **Visual Dialogue State Tracking for Question Generation.** AAAI, 2020. [paper](https://arxiv.org/pdf/1911.07928.pdf)\n   \n   *Wei Pang, Xiaojie Wang*\n\n7. **Interactive Classification by Asking Informative Questions.** ACL, 2020. [paper](https://arxiv.org/pdf/1911.03598.pdf)\n   \n   *Lili Yu, Howard Chen, Sida Wang, Tao Lei, Yoav Artzi*\n\n7. **Learning to Ask More: Semi-Autoregressive Sequential Question Generation under Dual-Graph Interaction.** ACL, 2020. [paper](https://www.aclweb.org/anthology/2020.acl-main.21.pdf) [dataset](https://github.com/ChaiZ-pku/Sequential-QG)\n   \n   *Zi Chai, Xiaojun Wan*\n\n8. **Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations.** EMNLP, 2020. [paper](https://arxiv.org/pdf/2004.14530.pdf) [codes](https://github.com/qipeng/stay-hungry-stay-focused)\n   \n   *Peng Qi, Yuhao Zhang, Christopher D. Manning*\n\n7. **ChainCQG: Flow-Aware Conversational Question Generation.** EACL, 2021. [paper](https://arxiv.org/pdf/2102.02864.pdf) [codes](https://github.com/searchableai/ChainCQG)\n    \n    *Jing Gu, Mostafa Mirshekari, Zhou Yu, Aaron Sisto*\n\n7. **GTM: A Generative Triple-wise Model for Conversational Question Generation.** ACL, 2021. [paper](https://arxiv.org/abs/2106.03635) \n    \n    *Lei Shen, Fandong Meng, Jinchao Zhang, Yang Feng, Jie Zhou*\n\n7. **Learning to Ask Conversational Questions by Optimizing Levenshtein Distance.** ACL, 2021. [paper](https://arxiv.org/abs/2106.15903) [codes](https://github.com/LZKSKY/CaSE_RISE)\n    \n    *Zhongkun Liu, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Maarten de Rijke, Ming Zhou*\n\n### [Asking Deep Questions](#asking-deep-questions)\n\nThis direction focuses on exploring how to ask deep questions that require high cognitive levels, such as multi-hop reasoning questions, mathematical questions, open-ended questions, and non-factoid questions. \n\n1. **Automatic Opinion Question Generation.** ICNLG, 2018. [paper](https://www.aclweb.org/anthology/W18-6518.pdf)\n   \n   *Yllias Chali, Tina Baghaee* \n\n3. **A Multi-language Platform for Generating Algebraic Mathematical Word Problems.** arxiv, 2019. [paper](https://arxiv.org/pdf/1912.01110.pdf)\n   \n   *Vijini Liyanage, Surangika Ranathunga*\n\n6. **Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums.** ACL, 2019. [paper](https://www.aclweb.org/anthology/P19-1497.pdf)\n   \n   *Zi Chai, Xinyu Xing, Xiaojun Wan, Bo Huang*\n\n7. **Learning to Ask Unanswerable Questions for Machine Reading Comprehension.** ACL, 2019. [paper](https://www.aclweb.org/anthology/P19-1415.pdf)\n   \n   *Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu*\n\n8. **Distant Supervised Why-Question Generation with Passage Self-Matching Attention.** IJCNN, 2019. [paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=8851781)\n   \n   *Jiaxin Hu, Zhixu Li, Renshou Wu, Hongling Wang, An Liu, Jiajie Xu, Pengpeng Zhao, Lei Zhao*\n\n9. **Conclusion-Supplement Answer Generation for Non-Factoid Questions.** AAAI, 2020. [paper](https://arxiv.org/pdf/1912.00864.pdf)\n   \n   *Makoto Nakatsuji, Sohei Okui*\n\n9. **Generating Multi-hop Reasoning Questions to Improve Machine Reading Comprehension.** WWW, 2020. [paper](https://dl.acm.org/doi/pdf/10.1145/3366423.3380114)\n   \n   *Jianxing Yu, Xiaojun Quan, Qinliang Su, Jian Yin*\n\n10. **Low-Resource Generation of Multi-hop Reasoning Questions.** ACL, 2020. [paper](https://www.aclweb.org/anthology/2020.acl-main.601.pdf)\n    \n    *Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin*\n\n11. **Semantic Graphs for Generating Deep Questions.** ACL, 2020. [paper](https://arxiv.org/pdf/2004.12704.pdf) [code](https://github.com/YuxiXie/SG-Deep-Question-Generation)\n    \n    *Liangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua, Min-Yen Kan*\n\n12. **Review-based Question Generation with Adaptive Instance Transfer and Augmentation.** ACL, 2020. [paper](https://www.aclweb.org/anthology/2020.acl-main.26.pdf)\n    \n    *Qian Yu, Lidong Bing, Qiong Zhang, Wai Lam, Luo Si*\n\n12. **Inquisitive Question Generation for High Level Text Comprehension.** EMNLP, 2020. [paper](https://arxiv.org/pdf/2010.01657.pdf) [dataset](https://github.com/wjko2/INQUISITIVE)\n    \n    *Wei-Jen Ko, Te-Yuan Chen, Yiyan Huang, Greg Durrett, Junyi Jessy Li*\n\n12. **Stronger Transformers for Neural Multi-Hop Question Generation.** ArXiv, 2020. [paper](https://arxiv.org/pdf/2010.11374.pdf)\n    \n    *Devendra Singh Sachan, Lingfei Wu, Mrinmaya Sachan, William Hamilton*\n\n12. **Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations.** ArXiv, 2020. [paper](https://arxiv.org/pdf/2010.06196.pdf)\n    \n    *Tianqiao Liu, Qian Fang, Wenbiao Ding, Zhongqin Wu, Zitao Liu*\n\n12. **Reinforced Multi-task Approach for Multi-hop Question Generation.** COLING, 2020. [paper](https://arxiv.org/pdf/2004.02143.pdf)\n    \n    *Deepak Gupta, Hardik Chauhan, Akella Ravi Tej, Asif Ekbal, Pushpak Bhattacharyya*\n\n12. **Exploring Question-Specific Rewards for Generating Deep Questions.** COLING, 2020. [paper](https://arxiv.org/pdf/2011.01102.pdf) [codes](https://github.com/YuxiXie/RL-for-Question-Generation)\n    \n    *Yuxi Xie, Liangming Pan, Dongzhe Wang, Min-Yen Kan, Yansong Feng*\n\n12. **Ask to Learn: A Study on Curiosity-driven Question Generation.** COLING, 2020. [paper](https://arxiv.org/pdf/1911.03350.pdf) [codes](https://github.com/YuxiXie/RL-for-Question-Generation)\n    \n    *Thomas Scialom, Jacopo Staiano*\n\n12. **EQG-RACE: Examination-Type Question Generation.** AAAI, 2021. [paper](https://arxiv.org/pdf/2012.06106.pdf)\n    \n    *Xin Jia, Wenjie Zhou, Xu Sun, Yunfang Wu*\n\n12. **CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering.** NeurIPS Workshop, 2021. [paper](https://arxiv.org/pdf/2010.16021.pdf) [codes](https://github.com/sunlab-osu/CliniQG4QA)\n    \n    *Xiang Yue, Xinliang Frederick Zhang, Ziyu Yao, Simon Lin, Huan Sun*\n\n7. **Quiz-Style Question Generation for News Stories.** WWW, 2021. [paper](https://arxiv.org/pdf/2102.09094.pdf) [codes](https://github.com/google-research-datasets/NewsQuizQA)\n    \n    *Adam D. Lelkes, Vinh Q. Tran, Cong Yu*\n\n7. **Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval.** arXiv, 2021. [paper](https://arxiv.org/pdf/2104.08801)\n    \n    *Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban, Siva Reddy*\n\n7. **Contrastive Multi-document Question Generation.** EACL, 2021. [paper](https://www.aclweb.org/anthology/2021.eacl-main.2.pdf) [codes](https://github.com/woonsangcho/contrast_qgen)\n    \n    *Woon Sang Cho, Yizhe Zhang, Sudha Rao, Asli Celikyilmaz, Chenyan Xiong, Jianfeng Gao, Mengdi Wang, Bill Dolan*\n\n7. **Controllable Open-ended Question Generation with A New Question Type Ontology.** ACL, 2021. [paper](https://arxiv.org/abs/2107.00152) [codes](https://shuyangcao.github.io/projects/ontology_open_ended_question)\n    \n    *Shuyang Cao, Lu Wang*\n\n### [Combining QA and QG](#Combining-QA-and-QG)\n\nThis direction investigate how to combine the task of QA and QG by multi-task learning or joint training. \n\n1. **Question Generation for Question Answering.** EMNLP,2017. [paper](https://www.aclweb.org/anthology/D17-1090)\n   \n   *Nan Duan, Duyu Tang, Peng Chen, Ming Zhou*\n\n2. **Learning to Collaborate for Question Answering and Asking.** NAACL, 2018. [paper](https://www.aclweb.org/anthology/N18-1141)\n   \n   *Duyu Tang, Nan Duan, Zhao Yan, Zhirui Zhang, Yibo Sun, Shujie Liu, Yuanhua Lv, Ming Zhou*\n\n3. **Generating Highly Relevant Questions.** EMNLP, 2019. [paper](https://arxiv.org/abs/1910.03401)\n   \n   *Jiazuo Qiu, Deyi Xiong*\n\n4. **Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds.** arxiv, 2019. [paper](https://arxiv.org/pdf/1911.02365.pdf)\n   \n   *Tassilo Klein, Moin Nabi*\n\n5. **Triple-Joint Modeling for Question Generation Using Cross-Task Autoencoder.** NLPCC, 2019. [paper](https://link.springer.com/chapter/10.1007/978-3-030-32236-6_26)\n   \n   *Hongling Wang, Renshou Wu, Zhixu Li, Zhongqing Wang, Zhigang Chen, Guodong Zhou*\n\n6. **Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering** EMNLP, 2019. [paper](https://arxiv.org/pdf/1909.06356.pdf) [code](https://github.com/ZhangShiyue/QGforQA)\n   \n   *Shiyue Zhang, Mohit Bansal*\n\n7. **Synthetic QA Corpora Generation with Roundtrip Consistency** ACL, 2019. [paper](https://arxiv.org/pdf/1906.05416.pdf)\n   \n   *Chris Alberti, Daniel Andor, Emily Pitler, Jacob Devlin, Michael Collins*\n\n7. **Unsupervised Question Answering by Cloze Translation** ACL, 2019. [paper](https://www.aclweb.org/anthology/P19-1484.pdf)\n   \n   *Patrick Lewis, Ludovic Denoyer, Sebastian Riedel*\n\n9. **Generating Multi-hop Reasoning Questions to Improve Machine Reading Comprehension.** WWW, 2020. [paper](https://dl.acm.org/doi/pdf/10.1145/3366423.3380114)\n   \n   *Jianxing Yu, Xiaojun Quan, Qinliang Su, Jian Yin*\n\n9. **Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering.** ACL, 2020. [paper](https://arxiv.org/pdf/2004.11892.pdf)\n   \n   *Alexander R. Fabbri, Patrick Ng, Zhiguo Wang, Ramesh Nallapati, Bing Xiang*\n\n9. **On the Importance of Diversity in Question Generation for QA.** ACL, 2020. [paper](https://www.aclweb.org/anthology/2020.acl-main.500.pdf)\n   \n   *Md Arafat Sultan, Shubham Chandel, Ramón Fernandez Astudillo, Vittorio Castelli*\n\n9. **End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems.** EMNLP, 2020. [paper](https://arxiv.org/pdf/2010.06028.pdf)\n   \n   *Siamak Shakeri, Cicero Nogueira dos Santos, Henry Zhu, Patrick Ng, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang*\n\n9. **Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space.** EMNLP, 2020. [paper](https://arxiv.org/pdf/2010.01475.pdf)\n   \n   *Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Jiancheng Lv, Nan Duan, Ming Zhou*\n\n9. **Training Question Answering Models From Synthetic Data.** EMNLP, 2020. [paper](https://arxiv.org/pdf/2002.09599.pdf)\n   \n   *Raul Puri, Ryan Spring, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro*\n\n7. **Unsupervised Multi-hop Question Answering by Question Generation.** NAACL, 2021. [paper](https://arxiv.org/pdf/2010.12623.pdf)\n    \n    *Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang*\n\n7. **Data-QuestEval: A Referenceless Metric for Data to Text Semantic Evaluation.** arXiv, 2021. [paper](https://arxiv.org/pdf/2104.07555)\n    \n    *Clément Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski, Sylvain Lamprier, Jacopo Staiano, Geoffrey Scoutheeten, Patrick Gallinari*\n\n7. **Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering** EMNLP, 2021. [paper](https://arxiv.org/pdf/2104.08202)\n    \n    *Or Honovich, Leshem Choshen, Roee Aharoni, Ella Neeman, Idan Szpektor, Omri Abend*\n\n7. **Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation** arXiv, 2021. [paper](https://arxiv.org/pdf/2104.08678)\n    \n    *Max Bartolo, Tristan Thrush, Robin Jia, Sebastian Riedel, Pontus Stenetorp, Douwe Kiela*\n\n7. **Cooperative Learning of Zero-Shot Machine Reading Comprehension.** arXiv, 2021. [paper](https://arxiv.org/pdf/2103.07449)\n    \n    *Hongyin Luo, Shang-Wen Li, Seunghak Yu, James Glass*\n\n7. **Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering.** EACL, 2021. [paper](https://www.aclweb.org/anthology/2021.eacl-main.244.pdf) [codes](https://github.com/xwhan/ProQA.git)\n    \n    *Wenhan Xiong, Hong Wang, William Yang Wang*\n\n7. **Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models.** NAACL, 2021. [paper](https://www.aclweb.org/anthology/2021.naacl-main.99.pdf) [codes](https://github.com/allenai/modularqa)\n    \n    *Tushar Khot, Daniel Khashabi, Kyle Richardson, Peter Clark, Ashish Sabharwal*\n\n7. **Improving Unsupervised Question Answering via Summarization-Informed Question Generation.** EMNLP, 2021. [paper](https://arxiv.org/pdf/2109.07954)\n\n    *Chenyang Lyu, Lifeng Shang, Yvette Graham, Jennifer Foster, Xin Jiang, Qun Liu*\n\n\n### [QG from knowledge graphs](#QG-from-knowledge-graphs)\n\nThis direction is about generating questions from a knowledge graph. \n\n1. **Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus.** ACL, 2016. [paper](https://arxiv.org/pdf/1603.06807.pdf) [dataset](https://www.agarciaduran.org)\n   \n   *Iulian Vlad Serban, Alberto García-Durán, Çaglar Gülçehre, Sungjin Ahn, Sarath Chandar, Aaron C. Courville, Yoshua Bengio*\n\n2. **Generating Natural Language Question-Answer Pairs from a Knowledge Graph Using a RNN Based Question Generation Model.** ACL, 2017. [paper](https://www.aclweb.org/anthology/E17-1036/)\n   \n   *Mitesh M. Khapra, Dinesh Raghu, Sachindra Joshi, Sathish Reddy*\n\n3. **Knowledge Questions from Knowledge Graphs.** ICTIR, 2017. [paper](https://arxiv.org/pdf/1610.09935.pdf)\n   \n   *Dominic Seyler, Mohamed Yahya, Klaus Berberich.*\n\n4. **Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types.** NAACL, 2018. [paper](https://arxiv.org/pdf/1802.06842.pdf) [code](https://github.com/NAACL2018Anonymous/submission)\n   \n   *Hady Elsahar, Christophe Gravier, Frederique Laforest.*\n\n5. **A Neural Question Generation System Based on Knowledge Base** NLPCC, 2018. [paper](https://link.springer.com/chapter/10.1007/978-3-319-99495-6_12)\n   \n   *Hao Wang, Xiaodong Zhang, Houfeng Wang*\n\n6. **Formal Query Generation for Question Answering over Knowledge Bases.** ESWC, 2018. [paper](https://link.springer.com/chapter/10.1007/978-3-319-93417-4_46)\n   \n   *Hamid Zafar, Giulio Napolitano, Jens Lehmann*\n\n7. **Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss.** EMNLP, 2019. [paper](https://www.aclweb.org/anthology/D19-1247.pdf)\n   \n   *Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao*\n\n8. **Difficulty-controllable Multi-hop Question Generation From Knowledge Graphs.** ISWC, 2019. [paper](https://arxiv.org/pdf/1807.03586.pdf)  [code\u0026dataset](https://github.com/liyuanfang/mhqg)\n   \n   *Vishwajeet Kumar, Yuncheng Hua, Ganesh Ramakrishnan, Guilin Qi, Lianli Gao, Yuan-Fang Li*\n\n9.  **How Question Generation Can Help Question Answering over Knowledge Base.** NLPCC, 2019. [paper](http://tcci.ccf.org.cn/conference/2019/papers/183.pdf)\n    \n    *Sen Hu, Lei Zou, Zhanxing Zhu*\n\n10.  **Toward Subgraph Guided Knowledge Graph Question Generation with Graph Neural Networks.** arXiv, 2020. [paper](https://arxiv.org/pdf/2004.06015.pdf)\n\n      *Yu Chen, Lingfei Wu, Mohammed J. Zaki*\n\n11.  **Generating Semantically Valid Adversarial Questions for TableQA.** arXiv, 2020. [paper](https://arxiv.org/pdf/2005.12696.pdf)\n\n      *Yi Zhu, Menglin Xia, Yiwei Zhou*\n\n12. **Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases.** COLING, 2020. [paper](https://arxiv.org/pdf/2010.03157.pdf)\n    \n    *Sheng Bi, Xiya Cheng, Yuan-Fang Li, Yongzhen Wang, Guilin Qi*\n\n\n### [Visual Question Generation](#visual-question-generation)\n\nAsking questions based on visual inputs (usually an image). \n\n1. **Generating Natural Questions About an Image** ACL, 2016. [paper](https://arxiv.org/pdf/1603.06059.pdf)\n   \n   *Nasrin Mostafazadeh, Ishan Misra, Jacob Devlin, Margaret Mitchell, Xiaodong He, Lucy Vanderwende*\n\n2. **Creativity: Generating Diverse Questions Using Variational Autoencoders** CVPR,2017. [paper](https://arxiv.org/pdf/1704.03493.pdf)\n   \n   *Unnat Jain, Ziyu Zhang, Alexander G. Schwing*\n\n3. **Automatic Generation of Grounded Visual Questions** IJCAI, 2017. [paper](https://www.ijcai.org/proceedings/2017/0592.pdf)\n   \n   *Shijie Zhang, Lizhen Qu, Shaodi You, Zhenglu Yang, Jiawan Zhang*\n\n4. **A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators** COLING, 2018. [paper](https://www.aclweb.org/anthology/C18-1150.pdf)\n   \n   *Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, Xuanjing Huang*\n\n5. **Customized Image Narrative Generation via Interactive Visual Question Generation and Answering** CVPR, 2018. [paper](https://arxiv.org/pdf/1805.00460.pdf)\n   \n   *Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada*\n\n6. **Multimodal Differential Network for Visual Question Generation** EMNLP, 2018. [paper](https://www.aclweb.org/anthology/D18-1434.pdf)\n   \n   *Badri Narayana Patro, Sandeep Kumar, Vinod Kumar Kurmi, Vinay P. Namboodiri*\n\n7. **A Question Type Driven Framework to Diversify Visual Question Generation** IJCAI, 2018. [paper](http://www.sdspeople.fudan.edu.cn/zywei/paper/fan-ijcai2018.pdf)\n   \n   *Zhihao Fan, Zhongyu Wei, Piji Li, Yanyan Lan, Xuanjing Huang*\n\n8. **Visual Question Generation as Dual Task of Visual Question Answering.** CVPR, 2018. [paper](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Visual_Question_Generation_CVPR_2018_paper.pdf)\n   \n   *Yikang Li, Nan Duan, Bolei Zhou, Xiao Chu, Wanli Ouyang, Xiaogang Wang, Ming Zhou* \n\n9. **Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering.** CVPR, 2018. [paper](https://arxiv.org/pdf/1803.11186.pdf)\n   \n   *Unnat Jain, Svetlana Lazebnik, Alexander Schwing*\n\n10. **Information Maximizing Visual Question Generation.** CVPR, 2019. [paper](https://arxiv.org/pdf/1903.11207.pdf)\n    \n    *Ranjay Krishna, Michael Bernstein, Li Fei-Fei*\n\n11. **What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog.** ACL, 2019. [paper](https://www.aclweb.org/anthology/P19-1646.pdf)\n    \n    *Pushkar Shukla, Carlos Elmadjian, Richika Sharan, Vivek Kulkarni, Matthew Turk, William Yang Wang*\n\n### [Distractor Generation](#distractor-generation)\n\nLearning to generate distractors for multi-choice questions. \n\n1. **Generating Questions and Multiple-Choice Answers using Semantic Analysis of Texts.** COLING, 2016. [paper](https://www.aclweb.org/anthology/C16-1107.pdf)\n\n   *Jun Araki, Dheeraj Rajagopal, Sreecharan Sankaranarayanan, Susan Holm, Yukari Yamakawa, Teruko Mitamura*\n\n2. **Distractor Generation for Multiple Choice Questions Using Learning to Rank.** NAACL Workshop, 2018. [paper](https://www.aclweb.org/anthology/W18-0533.pdf) [code](https://github.com/harrylclc/LTR-DG)\n\n   *Chen Liang, Xiao Yang, Neisarg Dave, Drew Wham, Bart Pursel, C. Lee Giles*\n\n3. **Generating Distractors for Reading Comprehension Questions from Real Examinations.** AAAI, 2019. [paper](https://arxiv.org/pdf/1809.02768.pdf)\n\n   *Yifan Gao, Lidong Bing, Piji Li, Irwin King, Michael R. Lyu*\n\n4. **Knowledge-Driven Distractor Generation for Cloze-style Multiple Choice Questions.** AAAI, 2021. [paper](https://arxiv.org/pdf/2004.09853.pdf)\n    \n    *Siyu Ren, Kenny Q. Zhu*\n\n### [Cross-lingual QG](#cross-lingual-QG)\n\nBuilding cross-lingual models to generate questions in low-resource languages. \n\n1. **Cross-Lingual Training for Automatic Question Generation.** ACL, 2019. [paper](https://arxiv.org/pdf/1906.02525.pdf) [dataset](https://www.cse.iitb.ac.in/~ganesh/HiQuAD/clqg/)\n   \n   *Vishwajeet Kumar, Nitish Joshi, Arijit Mukherjee, Ganesh Ramakrishnan, Preethi Jyothi*\n\n2. **Cross-Lingual Natural Language Generation via Pre-Training.** AAAI, 2020. [paper](https://arxiv.org/pdf/1909.10481.pdf)\n\n   *Zewen Chi, Li Dong, Furu Wei, Wenhui Wang, Xian-Ling Mao, Heyan Huang*\n\n7. **Quinductor: a multilingual data-driven method for generating reading-comprehension questions using Universal Dependencies.** arXiv, 2021. [paper](https://arxiv.org/pdf/2103.10121) [codes](https://github.com/dkalpakchi/quinductor)\n    \n    *Dmytro Kalpakchi, Johan Boye*\n\n### [Clarification Question Generation](#clarification-question-generation)\n\nLearning to ask clarification questions to better understand user intents in conversation, recommendation system, or search engine. \n\n1. **Are You Asking the Right Questions? Teaching Machines to Ask Clarification Questions.** ACL Workshop, 2017. [paper](https://www.aclweb.org/anthology/P17-3006.pdf)\n   \n   *Sudha Rao*\n\n2. **Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information.** ACL, 2018. [paper](https://arxiv.org/pdf/1805.04655.pdf) [code](https://github.com/raosudha89/ranking_clarification_questions)\n   \n   *Sudha Rao, Hal Daumé III*\n\n1. **Interpretation of Natural Language Rules in Conversational Machine Reading.** EMNLP, 2018. [paper](https://arxiv.org/pdf/1809.01494.pdf) [dataset](https://sharc-data.github.io/)\n   \n   *Marzieh Saeidi, Max Bartolo, Patrick Lewis, Sameer Singh, Tim Rocktäschel, Mike Sheldon, Guillaume Bouchard, Sebastian Riedel*\n\n1. **Answer-based Adversarial Training for Generating Clarification Questions.** NAACL, 2019. [paper](https://arxiv.org/pdf/1904.02281.pdf) [code](https://github.com/raosudha89/clarification_question_generation_pytorch)\n   \n   *Rao S, Daumé III H.*\n\n2. **Asking Clarifying Questions in Open-Domain Information-Seeking Conversations.** SIGIR, 2019. [paper](https://dl.acm.org/doi/pdf/10.1145/3331184.3331265) [dataset](https://github.com/aliannejadi/qulac)\n   \n   *Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, W. Bruce Croft*\n\n\n2. **Asking Clarification Questions in Knowledge-Based Question Answering.** EMNLP, 2019. [paper](https://www.aclweb.org/anthology/D19-1172.pdf) [dataset](https://github.com/msra-nlc/MSParS_V2.0)\n   \n   *Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, Pengcheng Yang, Qi Zeng, Ming Zhou, Xu Sun*\n\n\n1. **ClarQ: A large-scale and diverse dataset for Clarification Question Generation.** ACL, 2020. [paper](https://www.aclweb.org/anthology/2020.acl-main.651.pdf) [dataset](https://github.com/vaibhav4595/ClarQ)\n   \n   *Vaibhav Kumar, Alan W. black.*\n\n2. **Interactive Classification by Asking Informative Questions.** ACL, 2020. [paper](https://arxiv.org/pdf/1911.03598.pdf)\n   \n   *Lili Yu, Howard Chen, Sida Wang, Tao Lei, Yoav Artzi*\n\n2. **Towards Question-based Recommender Systems.** SIGIR, 2020. [paper](https://arxiv.org/pdf/2005.14255.pdf)\n   \n   *Jie Zou, Yifan Chen, Evangelos Kanoulas*\n\n2. **Generating Clarifying Questions for Information Retrieval.** WWW, 2020. [paper](http://hamedz.ir/assets/pub/zamani-www2020.pdf)\n   \n   *Hamed Zamani, Susan T. Dumais, Nick Craswell, Paul N. Bennett, and Gord Lueck*\n\n7. **Diverse and Specific Clarification Question Generation with Keywords** WWW, 2021. [paper](https://arxiv.org/pdf/2104.10317) [codes](https://github.com/blmoistawinde/KPCNet)\n    \n    *Zhiling Zhang, Kenny Q. Zhu*\n\n7. **Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing** EMNLP, 2021. [paper](https://arxiv.org/pdf/2103.02227)\n    \n    *Ao Zhang, Kun Wu, Lijie Wang, Zhenghua Li, Xinyan Xiao, Hua Wu, Min Zhang, Haifeng Wang*\n\n7. **Learning to Ask Appropriate Questions in Conversational Recommendation** SIGIR, 2021. [paper](https://arxiv.org/pdf/2105.04774) [codes](https://github.com/XuhuiRen/KBQG)\n    \n    *Xuhui Ren, Hongzhi Yin, Tong Chen, Hao Wang, Zi Huang, Kai Zheng*\n\n7. **Ask whats missing and whats useful: Improving Clarification Question Generation using Global Knowledge.** NAACL, 2021. [paper](https://www.aclweb.org/anthology/2021.naacl-main.340.pdf) [codes](https://github.com/microsoft/clarification-qgen-globalinfo)\n    \n    *Bodhisattwa Prasad Majumder, Sudha Rao, Michel Galley, Julian McAuley*\n\n## [Evaluation](#evaluation)\n\nThis direction investigates the mechanism behind question asking, and how to evaluate the quality of generated questions. \n\n1. **Question Asking as Program Generation.** NeurIPS, 2017. [paper](https://arxiv.org/pdf/1711.06351.pdf)\n   \n   *Anselm Rothe, Brenden M. Lake, Todd M. Gureckis.*\n\n2. **Towards a Better Metric for Evaluating Question Generation Systems.** EMNLP, 2018. [paper](https://www.aclweb.org/anthology/D18-1429/)\n   \n   *Preksha Nema, Mitesh M. Khapra.*\n\n3. **Evaluating Rewards for Question Generation Models.** NAACL, 2019. [paper](https://arxiv.org/pdf/1902.11049.pdf)\n   \n   *Tom Hosking and Sebastian Riedel.*\n\n## [Resources](#resources)\n\nQG-specific datasets and toolkits. \n\n1. **LearningQ: A Large-Scale Dataset for Educational Question Generation.** ICWSM, 2018. [paper](https://yangjiera.github.io/works/icwsm2018.pdf)\n   \n   *Guanliang Chen, Jie Yang, Claudia Hauff, Geert-Jan Houben.*\n\n2. **ParaQG: A System for Generating Questions and Answers from Paragraphs.** EMNLP Demo, 2019. [paper](https://arxiv.org/pdf/1909.01642.pdf)\n   \n   *Vishwajeet Kumar, Sivaanandh Muneeswaran, Ganesh Ramakrishnan, Yuan-Fang Li.*\n\n3. **How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions.** AAAI, 2020. [paper](https://arxiv.org/pdf/1911.09247.pdf) [code](https://github.com/ZeweiChu/MQR)\n   \n   *Zewei Chu, Mingda Chen, Jing Chen, Miaosen Wang, Kevin Gimpel, Manaal Faruqui, Xiance Si.*\n\n3. **ClarQ: A large-scale and diverse dataset for Clarification Question Generation.** ACL, 2020. [paper](https://www.aclweb.org/anthology/2020.acl-main.651.pdf) [dataset](https://github.com/vaibhav4595/ClarQ)\n   \n   *Vaibhav Kumar, Alan W. black.*\n\n3. [Toolkit] **Question Generation using transformers** . [github link](https://github.com/patil-suraj/question_generation)\n   \n   *Suraj Patil*\n\n12. **Inquisitive Question Generation for High Level Text Comprehension.** EMNLP, 2020. [paper](https://arxiv.org/pdf/2010.01657.pdf) [dataset](https://github.com/wjko2/INQUISITIVE)\n    \n    *Wei-Jen Ko, Te-Yuan Chen, Yiyan Huang, Greg Durrett, Junyi Jessy Li*\n\n7. **Quiz-Style Question Generation for News Stories.** WWW, 2021. [paper](https://arxiv.org/pdf/2102.09094.pdf) [codes](https://github.com/google-research-datasets/NewsQuizQA)\n    \n    *Adam D. Lelkes, Vinh Q. Tran, Cong Yu*\n\n7. **Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval.** EMNLP, 2021. [paper](https://arxiv.org/pdf/2104.08801)\n    \n    *Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban, Siva Reddy*\n\n6. **Automatically Generating Cause-and-Effect Questions from Passages.** EACL Workshop, 2021. [paper](https://www.aclweb.org/anthology/2021.bea-1.17.pdf) [codes](https://github.com/kstats/CausalQG)\n    \n    *Katherine Stasaski, Manav Rathod, Tony Tu, Yunfang Xiao, Marti A. Hearst*\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fteacherpeterpan%2FQuestion-Generation-Paper-List","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fteacherpeterpan%2FQuestion-Generation-Paper-List","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fteacherpeterpan%2FQuestion-Generation-Paper-List/lists"}