{"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/learning-to-ask-questions-in-open-domain","title":"Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders","arxiv_id":"1805.04843","date":"2018-05-13","proceeding":"ACL 2018 7","authors":["Yansen Wang","Chen-Yi Liu","Minlie Huang","Liqiang Nie"],"abstract":"Asking good questions in large-scale, open-domain conversational systems is\nquite significant yet rather untouched. This task, substantially different from\ntraditional question generation, requires to question not only with various\npatterns but also on diverse and relevant topics. We observe that a good\nquestion is a natural composition of {\\it interrogatives}, {\\it topic words},\nand {\\it ordinary words}. Interrogatives lexicalize the pattern of questioning,\ntopic words address the key information for topic transition in dialogue, and\nordinary words play syntactical and grammatical roles in making a natural\nsentence. We devise two typed decoders (\\textit{soft typed decoder} and\n\\textit{hard typed decoder}) in which a type distribution over the three types\nis estimated and used to modulate the final generation distribution. Extensive\nexperiments show that the typed decoders outperform state-of-the-art baselines\nand can generate more meaningful questions.","url_abs":"http://arxiv.org/abs/1805.04843v1","url_pdf":"http://arxiv.org/pdf/1805.04843v1.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":"learning-to-ask-questions-in-open-domain","repo_url":"https://github.com/victorywys/Learning2Ask_TypedDecoder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.04843","atlas_url":"https://app.syntology.ai/?focus=1805.04843","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}