{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/machine-comprehension-by-text-to-text-neural","title":"Machine Comprehension by Text-to-Text Neural Question Generation","arxiv_id":"1705.02012","date":"2017-05-04","proceeding":"WS 2017 8","authors":["Xingdi Yuan","Tong Wang","Caglar Gulcehre","Alessandro Sordoni","Philip Bachman","Sandeep Subramanian","Saizheng Zhang","Adam Trischler"],"abstract":"We propose a recurrent neural model that generates natural-language questions\nfrom documents, conditioned on answers. We show how to train the model using a\ncombination of supervised and reinforcement learning. After teacher forcing for\nstandard maximum likelihood training, we fine-tune the model using policy\ngradient techniques to maximize several rewards that measure question quality.\nMost notably, one of these rewards is the performance of a question-answering\nsystem. We motivate question generation as a means to improve the performance\nof question answering systems. Our model is trained and evaluated on the recent\nquestion-answering dataset SQuAD.","url_abs":"http://arxiv.org/abs/1705.02012v2","url_pdf":"http://arxiv.org/pdf/1705.02012v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"machine-comprehension-by-text-to-text-neural","repo_url":"https://github.com/GauthierDmn/question_generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"machine-comprehension-by-text-to-text-neural","repo_url":"https://github.com/bloomsburyai/question-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"machine-comprehension-by-text-to-text-neural","repo_url":"https://github.com/dangwalp/qg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"machine-comprehension-by-text-to-text-neural","repo_url":"https://github.com/trisongz/question-answering-lightning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.02012","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}