{"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/dialogue-response-selection-with-hierarchical","title":"Dialogue Response Selection with Hierarchical Curriculum Learning","arxiv_id":"2012.14756","date":"2020-12-29","proceeding":"ACL 2021 5","authors":["Yixuan Su","Deng Cai","Qingyu Zhou","Zibo Lin","Simon Baker","Yunbo Cao","Shuming Shi","Nigel Collier","Yan Wang"],"abstract":"We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-world scenarios, we propose a hierarchical curriculum learning framework that trains the matching model in an \"easy-to-difficult\" scheme. Our learning framework consists of two complementary curricula: (1) corpus-level curriculum (CC); and (2) instance-level curriculum (IC). In CC, the model gradually increases its ability in finding the matching clues between the dialogue context and a response candidate. As for IC, it progressively strengthens the model's ability in identifying the mismatching information between the dialogue context and a response candidate. Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics.","url_abs":"https://arxiv.org/abs/2012.14756v3","url_pdf":"https://arxiv.org/pdf/2012.14756v3.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":"dialogue-response-selection-with-hierarchical","repo_url":"https://github.com/yxuansu/HCL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"conversational-response-selection","task_name":"Conversational Response Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conversational-response-selection-on-douban-1","task":"Conversational Response Selection","dataset":"Douban","model":"SA-BERT+HCL","rank_in_archive_order":5,"of":16,"metrics":{"MAP":"0.639","MRR":"0.681","P@1":"0.514","R10@1":"0.330","R10@2":"0.531","R10@5":"0.858"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-e","task":"Conversational Response Selection","dataset":"E-commerce","model":"SA-BERT+HCL","rank_in_archive_order":7,"of":15,"metrics":{"R10@1":"0.721","R10@2":"0.896","R10@5":"0.993"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-rrs","task":"Conversational Response Selection","dataset":"RRS","model":"SA-BERT+HCL","rank_in_archive_order":3,"of":7,"metrics":{"MAP":"0.671","MRR":"0.683","P@1":"0.503","R10@1":"0.454","R10@2":"0.659","R10@5":"0.917"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.14756","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}