Question-Generation-Paper-List

A summary of must-read papers for Neural Question Generation (NQG)

• Contributed by Liangming Pan and Yuxi Xie.

Content

1. Survey
2. Models
2.1 Basic Seq2Seq Models	2.2 Encoding Answers
2.3 Linguistic Features	2.4 Question-specific Rewards
2.5 Content Selection	2.6 Question Type Modeling
2.7 Encode wider contexts	2.8 Other Directions
2. Applications
2.1 Difficulty Controllable QG	2.2 Conversational QG
2.3 Asking special questions	2.4 Answer-unaware QG
2.5 Unanswerable QG	2.6 Combining QA and QG
2.7 QG from knowledge graphs	2.8 Visual Question Generation
2.9 Distractor Generation
3. Evaluation
4. Resources

Survey papers

1. Recent Advances in Neural Question Generation. arxiv, 2018. paper

   Liangming Pan, Wenqiang Lei, Tat-Seng Chua, Min-Yen Kan.

Models

Basic Seq2Seq Models

Basic Seq2Seq models with attention to generate questions.

1. Learning to ask: Neural question generation for reading comprehension. ACL, 2017. paper

   Xinya Du, Junru Shao, Claire Cardie.

2. Neural question generation from text: A preliminary study. NLPCC, 2017. paper

   Qingyu Zhou, Nan Yang, Furu Wei, Chuanqi Tan, Hangbo Bao, Ming Zhou.

3. Machine comprehension by text-to-text neural question generation. Rep4NLP@ACL, 2017. paper

   Xingdi Yuan, Tong Wang, Çaglar Gülçehre, Alessandro Sordoni, Philip Bachman, Saizheng Zhang, Sandeep Subramanian, Adam Trischler

Encoding Answers

Applying various techniques to encode the answer information thus allowing for better quality answer-focused questions.

1. Answer-focused and Position-aware Neural Question Generation. EMNLP, 2018. paper

   Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang

2. Improving Neural Question Generation Using Answer Separation. AAAI, 2019. paper code

   Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung.

3. Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring. AAAI, 2020. paper

   Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Wu

Linguistic Features

Improve QG by incorporating various linguistic features into the QG process.

1. Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features. INLG, 2018. paper

   Vrindavan Harrison, Marilyn Walker

2. Automatic Question Generation using Relative Pronouns and Adverbs. ACL, 2018. paper

   Payal Khullar, Konigari Rachna, Mukul Hase, Manish Shrivastava

3. Learning to Generate Questions by Learning What not to Generate. WWW, 2019. paper code

   Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu.

4. Improving Neural Question Generation using World Knowledge. arXiv, 2019. paper

   Deepak Gupta, Kaheer Suleman, Mahmoud Adada, Andrew McNamara, Justin Harris

Question-specific Rewards

Improving the training via combining supervised and reinforcement learning to maximize question-specific rewards

1. Teaching Machines to Ask Questions. IJCAI, 2018. paper

   Kaichun Yao, Libo Zhang, Tiejian Luo, Lili Tao, Yanjun Wu

2. Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation arxiv, 2019. paper

   Yu Chen, Lingfei Wu, Mohammed J. Zaki

3. Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model NeurIPS Workshop, 2019. paper

   Yu Chen, Lingfei Wu, Mohammed J. Zaki

4. Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text CoNLL, 2019. paper

   Vishwajeet Kumar, Ganesh Ramakrishnan, Yuan-Fang Li

5. Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering EMNLP, 2019. paper code

   Shiyue Zhang, Mohit Bansal

Content Selection

Improve QG by considering how to select question-worthy contents (content selection) before asking a question.

1. Identifying Where to Focus in Reading Comprehension for Neural Question Generation. EMNLP, 2017. paper

   Xinya Du, Claire Cardie

2. Answer-based Adversarial Training for Generating Clarification Questions. NAACL, 2019. paper code

   Rao S, Daumé III H.

3. Learning to Generate Questions by Learning What not to Generate. WWW, 2019. paper code

   Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu.

4. Improving Question Generation With to the Point Context. EMNLP, 2019. paper

   Jingjing Li, Yifan Gao, Lidong Bing, Irwin King, Michael R. Lyu.

5. Weak Supervision Enhanced Generative Network for Question Generation. IJCAI, 2019. paper

   Yutong Wang, Jiyuan Zheng, Qijiong Liu, Zhou Zhao, Jun Xiao, Yueting Zhuang

6. A Multi-Agent Communication Framework for Question-Worthy Phrase Extraction and Question Generation. AAAI, 2019. paper

   Siyuan Wang, Zhongyu Wei, Zhihao Fan, Yang Liu, Xuanjing Huang

Question Type Modeling

Improve QG by explicitly modeling question types or interrogative words.

1. Question Generation for Question Answering. EMNLP,2017. paper

   Nan Duan, Duyu Tang, Peng Chen, Ming Zhou

2. Answer-focused and Position-aware Neural Question Generation. EMNLP, 2018. paper

   Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang

3. Let Me Know What to Ask: Interrogative-Word-Aware Question Generation EMNLP Workshop, 2019. paper

   Junmo Kang, Haritz Puerto San Roman, Sung-Hyon Myaeng

4. Question-type Driven Question Generation EMNLP, 2019. paper

   Wenjie Zhou, Minghua Zhang, Yunfang Wu

Encode Wider Contexts

Improve QG by incorporating wider contexts in the input passage.

1. Harvesting paragraph-level question-answer pairs from wikipedia. ACL, 2018. paper code&dataset

   Xinya Du, Claire Cardie

2. Leveraging Context Information for Natural Question Generation ACL, 2018. paper code

   Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea

3. Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks. EMNLP, 2018. paper

   Yao Zhao, Xiaochuan Ni, Yuanyuan Ding, Qifa Ke

4. Capturing Greater Context for Question Generation arxiv, 2019. paper

   Luu Anh Tuan, Darsh J Shah, Regina Barzilay

Other Directions

1. Cross-Lingual Training for Automatic Question Generation. ACL, 2019. paper dataset

   Vishwajeet Kumar, Nitish Joshi, Arijit Mukherjee, Ganesh Ramakrishnan, Preethi Jyothi

2. Generating Question-Answer Hierarchies. ACL, 2019. paper code

   Kalpesh Krishna and Mohit Iyyer.

3. Unified Language Model Pre-training for Natural Language Understanding and Generation. NeurIPS, 2019. paper code

   Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon

4. Can You Unpack That? Learning to Rewrite Questions-in-Context. EMNLP, 2019. paper

   Ahmed Elgohary, Denis Peskov, Jordan L. Boyd-Graber

5. Sequential Copying Networks. AAAI, 2018. paper

   Qingyu Zhou, Nan Yang, Furu Wei, Ming Zhou

Applications

Difficulty Controllable QG

Endowing the model with the ability to control the difficulty of the generated questions.

1. Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation. arxiv, 2019. paper

   Jie Zhao, Xiang Deng, Huan Sun.

2. Difficulty Controllable Generation of Reading Comprehension Questions. IJCAI, 2019. paper

   Yifan Gao, Lidong Bing, Wang Chen, Michael R. Lyu, Irwin King

3. Difficulty-controllable Multi-hop Question Generation From Knowledge Graphs. ISWC, 2019. paper code&dataset

   Vishwajeet Kumar, Yuncheng Hua, Ganesh Ramakrishnan, Guilin Qi, Lianli Gao, Yuan-Fang Li

Conversational QG

Learning to generate a series of coherent questions grounded in a question answering style conversation.

1. Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders. ACL, 2018. paper code dataset

   Yansen Wang, Chenyi Liu, Minlie Huang, Liqiang Nie

2. Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling. ACL, 2019. paper code

   Yifan Gao, Piji Li, Irwin King, Michael R. Lyu

3. Reinforced Dynamic Reasoning for Conversational Question Generation. ACL, 2019. paper code dataset

   Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun

4. Towards Answer-unaware Conversational Question Generation. ACL Workshop, 2019. paper

   Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi

Asking special questions

This direction focuses on exploring how to ask special types of questions, such as mathematical questions, open-ended questions, non-factoid questions, and clarification questions.

1. Are You Asking the Right Questions? Teaching Machines to Ask Clarification Questions. ACL Workshop, 2017. paper

   Sudha Rao

2. Automatic Opinion Question Generation. ICNLG, 2018. paper

   Yllias Chali, Tina Baghaee

3. A Multi-language Platform for Generating Algebraic Mathematical Word Problems. arxiv, 2019. paper

   Vijini Liyanage, Surangika Ranathunga

4. Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums. ACL, 2019. paper

   Zi Chai, Xinyu Xing, Xiaojun Wan, Bo Huang

5. Conclusion-Supplement Answer Generation for Non-Factoid Questions. AAAI, 2020. paper

   Makoto Nakatsuji, Sohei Okui

6. Answer-based Adversarial Training for Generating Clarification Questions. NAACL, 2019. paper code

   Rao S, Daumé III H.

7. Distant Supervised Why-Question Generation with Passage Self-Matching Attention. IJCNN, 2019. paper

   Jiaxin Hu, Zhixu Li, Renshou Wu, Hongling Wang, An Liu, Jiajie Xu, Pengpeng Zhao, Lei Zhao

Answer-unaware QG

In answer-unaware QG, the model does not require the target answer as an input to serve as the focus of asking. Therefore, the model should automatically identify question-worthy parts within the passage to ask.

1. Learning to ask: Neural question generation for reading comprehension. ACL, 2017. paper

   Xinya Du, Junru Shao, Claire Cardie.

2. Neural Models for Key Phrase Extraction and Question Generation. ACL Workshop, 2018. paper

   Sandeep Subramanian, Tong Wang, Xingdi Yuan, Saizheng Zhang, Adam Trischler, Yoshua Bengio

3. Self-Attention Architectures for Answer-Agnostic Neural Question Generation. ACL, 2019. paper

   Thomas Scialom, Benjamin Piwowarski, Jacopo Staiano.

Unanswerable QG

Learning to generate questions that cannot be answered by the input passage.

1. Learning to Ask Unanswerable Questions for Machine Reading Comprehension. ACL, 2019. paper

   Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu

Combining QA and QG

This direction investigate how to combine the task of QA and QG by multi-task learning or joint training.

1. Question Generation for Question Answering. EMNLP,2017. paper

   Nan Duan, Duyu Tang, Peng Chen, Ming Zhou

2. Learning to Collaborate for Question Answering and Asking. NAACL, 2018. paper

   Duyu Tang, Nan Duan, Zhao Yan, Zhirui Zhang, Yibo Sun, Shujie Liu, Yuanhua Lv, Ming Zhou

3. Generating Highly Relevant Questions. EMNLP, 2019. paper

   Jiazuo Qiu, Deyi Xiong

4. Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds. arxiv, 2019. paper

   Tassilo Klein, Moin Nabi

5. Triple-Joint Modeling for Question Generation Using Cross-Task Autoencoder. NLPCC, 2019. paper

   Hongling Wang, Renshou Wu, Zhixu Li, Zhongqing Wang, Zhigang Chen, Guodong Zhou

6. Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering EMNLP, 2019. paper code

   Shiyue Zhang, Mohit Bansal

QG from knowledge graphs

This direction is about generating questions from a knowledge graph.

1. Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus. ACL, 2016. paper dataset

   Iulian Vlad Serban, Alberto García-Durán, Çaglar Gülçehre, Sungjin Ahn, Sarath Chandar, Aaron C. Courville, Yoshua Bengio

2. Generating Natural Language Question-Answer Pairs from a Knowledge Graph Using a RNN Based Question Generation Model. ACL, 2017. paper

   Mitesh M. Khapra, Dinesh Raghu, Sachindra Joshi, Sathish Reddy

3. Knowledge Questions from Knowledge Graphs. ICTIR, 2017. paper

   Dominic Seyler, Mohamed Yahya, Klaus Berberich.

4. Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types. NAACL, 2018. paper code

   Hady Elsahar, Christophe Gravier, Frederique Laforest.

5. A Neural Question Generation System Based on Knowledge Base NLPCC, 2018. paper

   Hao Wang, Xiaodong Zhang, Houfeng Wang

6. Formal Query Generation for Question Answering over Knowledge Bases. ESWC, 2018. paper

   Hamid Zafar, Giulio Napolitano, Jens Lehmann

7. Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss. EMNLP, 2019. paper

   Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao

8. Difficulty-controllable Multi-hop Question Generation From Knowledge Graphs. ISWC, 2019. paper code&dataset

   Vishwajeet Kumar, Yuncheng Hua, Ganesh Ramakrishnan, Guilin Qi, Lianli Gao, Yuan-Fang Li

9. How Question Generation Can Help Question Answering over Knowledge Base. NLPCC, 2019. paper

   Sen Hu, Lei Zou, Zhanxing Zhu

Visual Question Generation

Asking questions based on visual inputs (usually an image).

1. Generating Natural Questions About an Image ACL, 2016. paper

   Nasrin Mostafazadeh, Ishan Misra, Jacob Devlin, Margaret Mitchell, Xiaodong He, Lucy Vanderwende

2. Creativity: Generating Diverse Questions Using Variational Autoencoders CVPR,2017. paper

   Unnat Jain, Ziyu Zhang, Alexander G. Schwing

3. Automatic Generation of Grounded Visual Questions IJCAI, 2017. paper

   Shijie Zhang, Lizhen Qu, Shaodi You, Zhenglu Yang, Jiawan Zhang

4. A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators COLING, 2018. paper

   Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, Xuanjing Huang

5. Customized Image Narrative Generation via Interactive Visual Question Generation and Answering CVPR, 2018. paper

   Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada

6. Multimodal Differential Network for Visual Question Generation EMNLP, 2018. paper

   Badri Narayana Patro, Sandeep Kumar, Vinod Kumar Kurmi, Vinay P. Namboodiri

7. A Question Type Driven Framework to Diversify Visual Question Generation IJCAI, 2018. paper

   Zhihao Fan, Zhongyu Wei, Piji Li, Yanyan Lan, Xuanjing Huang

8. Visual Question Generation as Dual Task of Visual Question Answering. CVPR, 2018. paper

   Yikang Li, Nan Duan, Bolei Zhou, Xiao Chu, Wanli Ouyang, Xiaogang Wang, Ming Zhou

9. Information Maximizing Visual Question Generation. CVPR, 2019. paper

   Ranjay Krishna, Michael Bernstein, Li Fei-Fei

Distractor Generation

Learning to generate distractors for multi-choice questions.

1. Generating Questions and Multiple-Choice Answers using Semantic Analysis of Texts. COLING, 2016. paper

   Jun Araki, Dheeraj Rajagopal, Sreecharan Sankaranarayanan, Susan Holm, Yukari Yamakawa, Teruko Mitamura

2. Distractor Generation for Multiple Choice Questions Using Learning to Rank. NAACL Workshop, 2018. paper code

   Chen Liang, Xiao Yang, Neisarg Dave, Drew Wham, Bart Pursel, C. Lee Giles

3. Generating Distractors for Reading Comprehension Questions from Real Examinations. AAAI, 2019. paper

   Yifan Gao, Lidong Bing, Piji Li, Irwin King, Michael R. Lyu

Evaluation

This direction investigates the mechanism behind question asking, and how to evaluate the quality of generated questions.

1. Question Asking as Program Generation. NeurIPS, 2017. paper

   Anselm Rothe, Brenden M. Lake, Todd M. Gureckis.

2. Towards a Better Metric for Evaluating Question Generation Systems. EMNLP, 2018. paper

   Preksha Nema, Mitesh M. Khapra.

3. Evaluating Rewards for Question Generation Models. NAACL, 2019. paper

   Tom Hosking and Sebastian Riedel.

Resources

QG-specific datasets and toolkits.

1. LearningQ: A Large-Scale Dataset for Educational Question Generation. ICWSM, 2018. paper

   Guanliang Chen, Jie Yang, Claudia Hauff, Geert-Jan Houben.

2. ParaQG: A System for Generating Questions and Answers from Paragraphs. EMNLP Demo, 2019. paper

   Vishwajeet Kumar, Sivaanandh Muneeswaran, Ganesh Ramakrishnan, Yuan-Fang Li.

3. How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions. AAAI, 2020. paper code

   Zewei Chu, Mingda Chen, Jing Chen, Miaosen Wang, Kevin Gimpel, Manaal Faruqui, Xiance Si.