{"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-good-questions-ranking","title":"Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information","arxiv_id":"1805.04655","date":"2018-05-12","proceeding":"ACL 2018 7","authors":["Sudha Rao","Hal Daumé III"],"abstract":"Inquiry is fundamental to communication, and machines cannot effectively\ncollaborate with humans unless they can ask questions. In this work, we build a\nneural network model for the task of ranking clarification questions. Our model\nis inspired by the idea of expected value of perfect information: a good\nquestion is one whose expected answer will be useful. We study this problem\nusing data from StackExchange, a plentiful online resource in which people\nroutinely ask clarifying questions to posts so that they can better offer\nassistance to the original poster. We create a dataset of clarification\nquestions consisting of ~77K posts paired with a clarification question (and\nanswer) from three domains of StackExchange: askubuntu, unix and superuser. We\nevaluate our model on 500 samples of this dataset against expert human\njudgments and demonstrate significant improvements over controlled baselines.","url_abs":"http://arxiv.org/abs/1805.04655v2","url_pdf":"http://arxiv.org/pdf/1805.04655v2.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-good-questions-ranking","repo_url":"https://github.com/raosudha89/ranking_clarification_questions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.04655","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}