{"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/enhanced-speaker-aware-multi-party-multi-turn","title":"Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension","arxiv_id":"2109.04066","date":"2021-09-09","proceeding":null,"authors":["Xinbei Ma","Zhuosheng Zhang","Hai Zhao"],"abstract":"Multi-party multi-turn dialogue comprehension brings unprecedented challenges on handling the complicated scenarios from multiple speakers and criss-crossed discourse relationship among speaker-aware utterances. Most existing methods deal with dialogue contexts as plain texts and pay insufficient attention to the crucial speaker-aware clues. In this work, we propose an enhanced speaker-aware model with masking attention and heterogeneous graph networks to comprehensively capture discourse clues from both sides of speaker property and speaker-aware relationships. With such comprehensive speaker-aware modeling, experimental results show that our speaker-aware model helps achieves state-of-the-art performance on the benchmark dataset Molweni. Case analysis shows that our model enhances the connections between utterances and their own speakers and captures the speaker-aware discourse relations, which are critical for dialogue modeling.","url_abs":"https://arxiv.org/abs/2109.04066v1","url_pdf":"https://arxiv.org/pdf/2109.04066v1.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":[],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-friendsqa","task":"Question Answering","dataset":"FriendsQA","model":"Ma et al. - ELECTRA","rank_in_archive_order":1,"of":6,"metrics":{"EM":"58.7","F1":"75.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-molweni","task":"Question Answering","dataset":"Molweni","model":"Ma et al. - ELECTRA","rank_in_archive_order":1,"of":4,"metrics":{"EM":"58.6","F1":"72.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.04066","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}