{"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/speaker-aware-bert-for-multi-turn-response","title":"Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots","arxiv_id":"2004.03588","date":"2020-04-07","proceeding":null,"authors":["Jia-Chen Gu","Tianda Li","Quan Liu","Zhen-Hua Ling","Zhiming Su","Si Wei","Xiaodan Zhu"],"abstract":"In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make the model aware of the speaker change information, which is an important and intrinsic property of multi-turn dialogues. Furthermore, a speaker-aware disentanglement strategy is proposed to tackle the entangled dialogues. This strategy selects a small number of most important utterances as the filtered context according to the speakers' information in them. Finally, domain adaptation is performed to incorporate the in-domain knowledge into pre-trained language models. Experiments on five public datasets show that our proposed model outperforms the present models on all metrics by large margins and achieves new state-of-the-art performances for multi-turn response selection.","url_abs":"https://arxiv.org/abs/2004.03588v2","url_pdf":"https://arxiv.org/pdf/2004.03588v2.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":"speaker-aware-bert-for-multi-turn-response","repo_url":"https://github.com/JasonForJoy/SA-BERT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"speaker-aware-bert-for-multi-turn-response","repo_url":"https://github.com/JasonForJoy/BERT-for-Response-Selection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"conversational-response-selection","task_name":"Conversational Response Selection"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conversational-response-selection-on-douban-1","task":"Conversational Response Selection","dataset":"Douban","model":"SA-BERT","rank_in_archive_order":8,"of":16,"metrics":{"MAP":"0.619","MRR":"0.659","P@1":"0.496","R10@1":"0.313","R10@2":"0.481","R10@5":"0.847"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-e","task":"Conversational Response Selection","dataset":"E-commerce","model":"SA-BERT","rank_in_archive_order":8,"of":15,"metrics":{"R10@1":"0.704","R10@2":"0.879","R10@5":"0.985"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-rrs","task":"Conversational Response Selection","dataset":"RRS","model":"SA-BERT+BERT-FP","rank_in_archive_order":2,"of":7,"metrics":{"MAP":"0.701","MRR":"0.715","P@1":"0.555","R10@1":"0.497","R10@2":"0.685","R10@5":"0.931"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-rrs-1","task":"Conversational Response Selection","dataset":"RRS Ranking Test","model":"SA-BERT+BERT-FP","rank_in_archive_order":2,"of":4,"metrics":{"NDCG@3":"0.674","NDCG@5":"0.753"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-ubuntu-1","task":"Conversational Response Selection","dataset":"Ubuntu Dialogue (v1, Ranking)","model":"SA-BERT","rank_in_archive_order":11,"of":25,"metrics":{"R10@1":"0.855","R10@2":"0.928","R10@5":"0.983","R2@1":"0.965"},"uses_additional_data":false},{"leaderboard":"/sota/conversational-response-selection-on-ubuntu-3","task":"Conversational Response Selection","dataset":"Ubuntu IRC","model":"SA-BERT","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"60.42"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.03588","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}