{"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/improving-neural-question-generation-using","title":"Improving Neural Question Generation using Answer Separation","arxiv_id":"1809.02393","date":"2018-09-07","proceeding":null,"authors":["Yanghoon Kim","Hwanhee Lee","Joongbo Shin","Kyomin Jung"],"abstract":"Neural question generation (NQG) is the task of generating a question from a\ngiven passage with deep neural networks. Previous NQG models suffer from a\nproblem that a significant proportion of the generated questions include words\nin the question target, resulting in the generation of unintended questions. In\nthis paper, we propose answer-separated seq2seq, which better utilizes the\ninformation from both the passage and the target answer. By replacing the\ntarget answer in the original passage with a special token, our model learns to\nidentify which interrogative word should be used. We also propose a new module\ntermed keyword-net, which helps the model better capture the key information in\nthe target answer and generate an appropriate question. Experimental results\ndemonstrate that our answer separation method significantly reduces the number\nof improper questions which include answers. Consequently, our model\nsignificantly outperforms previous state-of-the-art NQG models.","url_abs":"http://arxiv.org/abs/1809.02393v2","url_pdf":"http://arxiv.org/pdf/1809.02393v2.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":"improving-neural-question-generation-using","repo_url":"https://github.com/yanghoonkim/neural_question_generation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.02393","atlas_url":"https://app.syntology.ai/?focus=1809.02393","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}