{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T18:32:45Z","timestamp":1774117965124,"version":"3.50.1"},"reference-count":75,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176187"],"award-info":[{"award-number":["62176187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Social Science Fund of the Ministry of Education","award":["20YJA740062"],"award-info":[{"award-number":["20YJA740062"]}]},{"name":"CCF-Kuaishou Large Model Explorer Fund"},{"name":"CCF-Baidu Open Fund"},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2025,1,31]]},"abstract":"<jats:p>\n            Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement requires the full understanding and harnessing of the intrinsic discourse attribute. In this article, we propose enhancing dialogue disentanglement by taking full advantage of the dialogue discourse characteristics. First of all,\n            <jats:italic>in feature encoding stage<\/jats:italic>\n            , we construct the heterogeneous graph representations to model the various dialogue-specific discourse structural features, including the static speaker-role structures (i.e., speaker-utterance and speaker-mentioning structure) and the dynamic contextual structures (i.e., the utterance-distance and partial-replying structure). We then develop a structure-aware framework to integrate the rich structural features for better modeling the conversational semantic context. Second,\n            <jats:italic>in model learning stage<\/jats:italic>\n            , we perform optimization with a hierarchical ranking loss mechanism, which groups dialogue utterances into different discourse levels and carries training covering pairwise and session-wise levels hierarchically. Third,\n            <jats:italic>in inference stage<\/jats:italic>\n            , we devise an easy-first decoding algorithm, which performs utterance pairing under the easy-to-hard manner with a global context, breaking the constraint of traditional sequential decoding order. On two benchmark datasets, our overall system achieves new state-of-the-art performances on all evaluations. In-depth analyses further demonstrate the efficacy of each proposed idea and also reveal how our methods help advance the task. Our work has great potential to facilitate broader multi-party multi-thread dialogue applications.\n          <\/jats:p>","DOI":"10.1145\/3698191","type":"journal-article","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T15:05:33Z","timestamp":1727795133000},"page":"1-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Revisiting Conversation Discourse for Dialogue Disentanglement"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-5540","authenticated-orcid":false,"given":"Bobo","family":"Li","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1816-1761","authenticated-orcid":false,"given":"Fei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6192-1194","authenticated-orcid":false,"given":"Shengqiong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9973-3305","authenticated-orcid":false,"given":"Lizi","family":"Liao","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1791-3159","authenticated-orcid":false,"given":"Yinwei","family":"Wei","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-seng","family":"Chua","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9613-5927","authenticated-orcid":false,"given":"Donghong","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]}],"member":"320","published-online":{"date-parts":[[2024,11,30]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"26","volume-title":"Proceedings of the 5th International Conference on Weblogs and Social Media","author":"Aumayr Erik","year":"2011","unstructured":"Erik Aumayr, Jeffrey Chan, and Conor Hayes. 2011. Reconstruction of threaded conversations in online discussion forums. In Proceedings of the 5th International Conference on Weblogs and Social Media, 26\u201333."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449917"},{"key":"e_1_3_2_4_2","first-page":"1877","volume-title":"Proceedings of the Neural Information Processing Systems","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Proceedings of the Neural Information Processing Systems, 1877\u20131901."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557392"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.suki-1.2"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1284"},{"key":"e_1_3_2_8_2","first-page":"4171","volume-title":"Proceedings of the North American Chapter of the Association for Computational Linguistics","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the North American Chapter of the Association for Computational Linguistics, 4171\u20134186."},{"key":"e_1_3_2_9_2","first-page":"834","volume-title":"Proceedings of the Association for Computational Linguistics-08: HLT","author":"Elsner Micha","year":"2008","unstructured":"Micha Elsner and Eugene Charniak. 2008. You talking to me? A corpus and algorithm for conversation disentanglement. In Proceedings of the Association for Computational Linguistics-08: HLT, 834\u2013842."},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Micha Elsner and Eugene Charniak. 2010. Disentangling chat. Computational Linguistics 36 3 (2010) 389\u2013409.","DOI":"10.1162\/coli_a_00003"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/570"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.10"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_3_2_14_2","first-page":"742","volume-title":"Proceedings of the North American Chapter of the Association for Computational Linguistics","author":"Goldberg Yoav","year":"2010","unstructured":"Yoav Goldberg and Michael Elhadad. 2010. An efficient algorithm for easy-first non-directional dependency parsing. In Proceedings of the North American Chapter of the Association for Computational Linguistics, 742\u2013750."},{"key":"e_1_3_2_15_2","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross B. Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2017. Accurate large minibatch SGD: Training ImageNet in 1 hour. arXiv:1706.02677. Retrieved from https:\/\/arxiv.org\/abs\/1706.02677"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.349"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.185"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_20_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In Proceedings of the International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.217"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383123"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"e_1_3_2_24_2","first-page":"259","volume-title":"Proceedings of the International Conference on Computational Linguistics","author":"Jiang Shenhao","year":"2018","unstructured":"Shenhao Jiang, Animesh Prasad, Min-Yen Kan, and Kazunari Sugiyama. 2018. Identifying emergent research trends by key authors and phrases. In Proceedings of the International Conference on Computational Linguistics, 259\u2013269."},{"key":"e_1_3_2_25_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413753"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1374"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1232"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.505"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.370"},{"key":"e_1_3_2_31_2","unstructured":"Tianda Li Jia-Chen Gu Xiaodan Zhu Quan Liu Zhen-Hua Ling Zhiming Su and Si Wei. 2020. DialBERT: A hierarchical pre-trained model for conversation disentanglement. arXiv:2004.03760. Retrieved from https:\/\/arxiv.org\/abs\/2004.03760"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.171"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531794"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17575"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/535"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1543"},{"key":"e_1_3_2_38_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In Proceedings of the International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.23"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_41_2","unstructured":"Aaron F. McDaid Derek Greene and Neil J. Hurley. 2011. Normalized mutual information to evaluate overlapping community finding algorithms. arXiv:1110.2515. Retrieved from https:\/\/arxiv.org\/abs\/1110.2515"},{"key":"e_1_3_2_42_2","first-page":"615","volume-title":"Proceedings of the 8th International Joint Conference on Natural Language Processing","author":"Mehri Shikib","year":"2017","unstructured":"Shikib Mehri and Giuseppe Carenini. 2017. Chat disentanglement: Identifying semantic reply relationships with random forests and recurrent neural networks. In Proceedings of the 8th International Joint Conference on Natural Language Processing, 615\u2013623."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45167-9_14"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12140"},{"key":"e_1_3_2_45_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Merity Stephen","year":"2018","unstructured":"Stephen Merity, Nitish Shirish Keskar, and Richard Socher. 2018. Regularizing and optimizing LSTM language models. In Proceedings of the International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_46_2","first-page":"807","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Nair Vinod","year":"2010","unstructured":"Vinod Nair and Geoffrey E. Hinton. 2010. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the International Conference on Machine Learning, 807\u2013814."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.279"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.5"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.85"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1196"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3432726"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747123"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10983"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148180"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583380"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_58_2","first-page":"1139","volume-title":"Proceedings of the 30th International Conference on Machine Learning","volume":"28","author":"Sutskever Ilya","year":"2013","unstructured":"Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. 2013. On the importance of initialization and momentum in deep learning. In Proceedings of the 30th International Conference on Machine Learning, Vol. 28. PMLR, 1139\u20131147."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1682"},{"key":"e_1_3_2_60_2","volume-title":"Proceedings of the 4th International Conference on Language Resources and Evaluation","author":"Traum David R.","year":"2004","unstructured":"David R. Traum, Susan Robinson, and Jens Stephan. 2004. Evaluation of multi-party virtual reality dialogue interaction. In Proceedings of the 4th International Conference on Language Resources and Evaluation."},{"key":"e_1_3_2_61_2","first-page":"5998","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems, 5998\u20136008."},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570430"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583420"},{"key":"e_1_3_2_64_2","first-page":"4824","volume-title":"Proceedings of the Neural Information Processing Systems","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the Neural Information Processing Systems, 4824\u201324837."},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450352"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449939"},{"key":"e_1_3_2_67_2","first-page":"5372","volume-title":"Proceedings of the International Conference on Computational Linguistics","author":"Yu Nan","year":"2022","unstructured":"Nan Yu, Guohong Fu, and Min Zhang. 2022. Speaker-aware discourse parsing on multi-party dialogues. In Proceedings of the International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 5372\u20135382."},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.512"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1124"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3522763"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3058616"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313598"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17711"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557581"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6524"},{"key":"e_1_3_2_76_2","first-page":"1","volume-title":"Proceedings of the Annual Workshop of the Australasian Language Technology Association","author":"Zhu Rongxin","year":"2021","unstructured":"Rongxin Zhu, Jey Han Lau, and Jianzhong Qi. 2021. Findings on conversation disentanglement. In Proceedings of the Annual Workshop of the Australasian Language Technology Association, 1\u201311."}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698191","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:18Z","timestamp":1750295838000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,30]]},"references-count":75,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1,31]]}},"alternative-id":["10.1145\/3698191"],"URL":"https:\/\/doi.org\/10.1145\/3698191","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,30]]},"assertion":[{"value":"2023-06-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}