{"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/addressee-and-response-selection-in-multi","title":"Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs","arxiv_id":"1709.04005","date":"2017-09-12","proceeding":null,"authors":["Rui Zhang","Honglak Lee","Lazaros Polymenakos","Dragomir Radev"],"abstract":"In this paper, we study the problem of addressee and response selection in\nmulti-party conversations. Understanding multi-party conversations is\nchallenging because of complex speaker interactions: multiple speakers exchange\nmessages with each other, playing different roles (sender, addressee,\nobserver), and these roles vary across turns. To tackle this challenge, we\npropose the Speaker Interaction Recurrent Neural Network (SI-RNN). Whereas the\nprevious state-of-the-art system updated speaker embeddings only for the\nsender, SI-RNN uses a novel dialog encoder to update speaker embeddings in a\nrole-sensitive way. Additionally, unlike the previous work that selected the\naddressee and response separately, SI-RNN selects them jointly by viewing the\ntask as a sequence prediction problem. Experimental results show that SI-RNN\nsignificantly improves the accuracy of addressee and response selection,\nparticularly in complex conversations with many speakers and responses to\ndistant messages many turns in the past.","url_abs":"http://arxiv.org/abs/1709.04005v2","url_pdf":"http://arxiv.org/pdf/1709.04005v2.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":"addressee-and-response-selection-in-multi","repo_url":"https://github.com/ryanzhumich/sirnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"conversational-response-selection","task_name":"Conversational Response Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conversational-response-selection-on-ubuntu-3","task":"Conversational Response Selection","dataset":"Ubuntu IRC","model":"SIRNN","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"40.83"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.04005","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}