{"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/interactive-matching-network-for-multi-turn","title":"Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots","arxiv_id":"1901.01824","date":"2019-01-07","proceeding":null,"authors":["Jia-Chen Gu","Zhen-Hua Ling","Quan Liu"],"abstract":"In this paper, we propose an interactive matching network (IMN) for the multi-turn response selection task. First, IMN constructs word representations from three aspects to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE), which is capable of encoding sentences hierarchically and generating more descriptive representations by aggregating with an attention mechanism, is designed. Finally, the bidirectional interactions between whole multi-turn contexts and response candidates are calculated to derive the matching information between them. Experiments on four public datasets show that IMN outperforms the baseline models on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection.","url_abs":"https://arxiv.org/abs/1901.01824v2","url_pdf":"https://arxiv.org/pdf/1901.01824v2.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":"interactive-matching-network-for-multi-turn","repo_url":"https://github.com/JasonForJoy/IMN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"conversational-response-selection","task_name":"Conversational Response Selection"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conversational-response-selection-on-douban-1","task":"Conversational Response Selection","dataset":"Douban","model":"IMN","rank_in_archive_order":13,"of":16,"metrics":{"MAP":"0.570","MRR":"0.615","P@1":"0.433","R10@1":"0.262","R10@2":"0.452","R10@5":"0.789"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-e","task":"Conversational Response Selection","dataset":"E-commerce","model":"IMN","rank_in_archive_order":9,"of":15,"metrics":{"R10@1":"0.621","R10@2":"0.797","R10@5":"0.964"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-ubuntu-1","task":"Conversational Response Selection","dataset":"Ubuntu Dialogue (v1, Ranking)","model":"IMN","rank_in_archive_order":16,"of":25,"metrics":{"R10@1":"0.794","R10@2":"0.889","R10@5":"0.974","R2@1":"0.946"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.01824","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}