{"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/large-scale-answerer-in-questioners-mind-for","title":"Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation","arxiv_id":"1902.08355","date":"2019-02-22","proceeding":"ICLR 2019 5","authors":["Sang-Woo Lee","Tong Gao","Sohee Yang","Jaejun Yoo","Jung-Woo Ha"],"abstract":"Answerer in Questioner's Mind (AQM) is an information-theoretic framework\nthat has been recently proposed for task-oriented dialog systems. AQM benefits\nfrom asking a question that would maximize the information gain when it is\nasked. However, due to its intrinsic nature of explicitly calculating the\ninformation gain, AQM has a limitation when the solution space is very large.\nTo address this, we propose AQM+ that can deal with a large-scale problem and\nask a question that is more coherent to the current context of the dialog. We\nevaluate our method on GuessWhich, a challenging task-oriented visual dialog\nproblem, where the number of candidate classes is near 10K. Our experimental\nresults and ablation studies show that AQM+ outperforms the state-of-the-art\nmodels by a remarkable margin with a reasonable approximation. In particular,\nthe proposed AQM+ reduces more than 60% of error as the dialog proceeds, while\nthe comparative algorithms diminish the error by less than 6%. Based on our\nresults, we argue that AQM+ is a general task-oriented dialog algorithm that\ncan be applied for non-yes-or-no responses.","url_abs":"http://arxiv.org/abs/1902.08355v1","url_pdf":"http://arxiv.org/pdf/1902.08355v1.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":"large-scale-answerer-in-questioners-mind-for","repo_url":"https://github.com/naver/aqm-plus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"},{"task_slug":"visual-dialogue","task_name":"Visual Dialog"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}