{"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/answer-based-adversarial-training-for","title":"Answer-based Adversarial Training for Generating Clarification Questions","arxiv_id":"1904.02281","date":"2019-04-04","proceeding":"NAACL 2019 6","authors":["Sudha Rao","Hal Daumé III"],"abstract":"We present an approach for generating clarification questions with the goal\nof eliciting new information that would make the given textual context more\ncomplete. We propose that modeling hypothetical answers (to clarification\nquestions) as latent variables can guide our approach into generating more\nuseful clarification questions. We develop a Generative Adversarial Network\n(GAN) where the generator is a sequence-to-sequence model and the discriminator\nis a utility function that models the value of updating the context with the\nanswer to the clarification question. We evaluate on two datasets, using both\nautomatic metrics and human judgments of usefulness, specificity and relevance,\nshowing that our approach outperforms both a retrieval-based model and\nablations that exclude the utility model and the adversarial training.","url_abs":"http://arxiv.org/abs/1904.02281v1","url_pdf":"http://arxiv.org/pdf/1904.02281v1.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":"answer-based-adversarial-training-for","repo_url":"https://github.com/raosudha89/clarification_question_generation_pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.02281","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}