{"type":"ScholarlyArticle","title":"MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning","authors":[{"name":"Ziyou Jiang","slug":"ziyou-jiang","given":"Ziyou","family":"Jiang","affiliation":"Laboratory for Internet Software Technologies , Institute of Software Chinese Academy of Sciences; University of Chinese Academy of Sciences , Beijing , China"},{"name":"Lin Shi","slug":"lin-shi","given":"Lin","family":"Shi","affiliation":"Laboratory for Internet Software Technologies , Institute of Software Chinese Academy of Sciences; University of Chinese Academy of Sciences , Beijing , China"},{"name":"Celia Chen","slug":"celia-chen","given":"Celia","family":"Chen","affiliation":"Department of Computer Science , Occidental College , Los Angeles , CA , USA"},{"name":"Fangwen Mu","slug":"fangwen-mu","given":"Fangwen","family":"Mu","affiliation":"Laboratory for Internet Software Technologies , Institute of Software Chinese Academy of Sciences; University of Chinese Academy of Sciences , Beijing , China"},{"name":"Yumin Zhang","slug":"yumin-zhang","given":"Yumin","family":"Zhang","affiliation":"Laboratory for Internet Software Technologies , Institute of Software Chinese Academy of Sciences; University of Chinese Academy of Sciences , Beijing , China"},{"name":"Qing Wang","slug":"qing-wang","given":"Qing","family":"Wang","affiliation":"Laboratory for Internet Software Technologies , Institute of Software Chinese Academy of Sciences; State Key Laboratory of Computer Sciences , Institute of Software Chinese Academy of Sciences; Science&Technology on Integrated Information System Laboratory , Institute of Software Chinese Academy of Sciences; University of Chinese Academy of Sciences , Beijing , China"}],"abstract":"The main goal of dialogue disentanglement is to separate the mixed utterances from a chat slice into independent dialogues. Existing models often utilize either an utterance-to-utterance (U2U) prediction to determine whether two utterances that have the “reply-to” relationship belong to one dialogue, or an utterance-to-thread (U2T) prediction to determine which dialogue-thread a given utterance should belong to. Inspired by mutual leaning, we propose MuiDial, a novel dialogue disentanglement model, to exploit the intent of each utterance and feed the intent to a mutual learning U2U-U2T disentanglement model. Experimental results and in-depth analysis on several benchmark datasets demonstrate the effectiveness and generalizability of our approach.","doi":"10.24963/ijcai.2022/578","url":"https://ijcai.org/proceedings/2022/578","pdf":"https://ijcai.org/proceedings/2022/0578.pdf","markdown":"https://ijcai.org/proceedings/2022/578.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/578","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Natural Language Processing","track":"Main Track","number":578,"pages":{"first":4164,"last":4170},"keywords":["Natural Language Processing: Dialogue and Interactive Systems","Natural Language Processing: Knowledge Extraction","Natural Language Processing: Applications"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986452","length_sec":81,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984595","length_sec":345,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chen and Manning, 2014] Danqi Chen and Christopher D. Manning. A fast and accurate dependency parser using neural networks. In EMNLP, pages 740-750, 2014.","title":"A fast and accurate dependency parser using neural networks","authors":"Chen, Manning, Danqi Chen, Christopher D Manning","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understand- ing. In NAACL-HLT, pages 4171-4186, 2019.","title":"BERT: pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Elsner and Charniak, 2010] Micha Elsner and Eugene Charniak. Disentangling chat. Comput. Linguistics, 36(3):389-409, 2010.","title":"Disentangling chat","authors":"Charniak Elsner, Micha Elsner, Eugene Charniak","year":"2010","venue":"Comput. Linguistics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Comput., 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural Comput","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Jiang et al., 2018] Jyun-Yu Jiang, Francine Chen, Yan-Ying Chen, and Wei Wang. Learning to disentangle interleaved conversational threads with a siamese hierarchical network and similarity ranking. In NAACL-HLT, pages 1812-1822, June 2018.","title":"Learning to disentangle interleaved conversational threads with a siamese hierarchical network and similarity ranking","authors":"Jyun-Yu Jiang, Francine Chen, Yan-Ying Chen, Wei Wang","year":"2018","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jiang et al., 2021] Ziyou Jiang, Lin Shi, Celia Chen, Jun Hu, and Qing Wang. Dialogue disentanglement in soft- ware engineering: How far are we? In IJCAI, pages 3822- 3828, 8 2021.","title":"Dialogue disentanglement in software engineering: How far are we?","authors":"Jiang","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/526"},{"position":7,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kummerfeld et al., 2019] Jonathan K. Kummerfeld, Sai R. Gouravajhala, Joseph Peper, Vignesh Athreya, Chulaka Gunasekara, Jatin Ganhotra, Siva Sankalp Patel, Lazaros Polymenakos, and Walter S. Lasecki. A large-scale corpus for conversation disentanglement. In ACL, pages 3846- 3856, July 2019.","title":"A large-scale corpus for conversation disentanglement","authors":"Jonathan K Kummerfeld, R Sai, Joseph Gouravajhala, Vignesh Peper, Chulaka Athreya, Jatin Gunasekara, Ganhotra, Sankalp Siva, Lazaros Patel, Walter S Polymenakos, Lasecki","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Li et al., 2020] Tianda Li, Jia-Chen Gu, Xiaodan Zhu, Quan Liu, Zhen-Hua Ling, Zhiming Su, and Si Wei. Dialbert: A hierarchical pre-trained model for conversation disentan- glement. arXiv preprint arXiv:2004.03760, 2020.","title":"Dialbert: A hierarchical pre-trained model for conversation disentanglement","authors":"Tianda Li, Jia-Chen Gu, Xiaodan Zhu, Quan Liu, Zhen-Hua Ling, Zhiming Su, Si Wei","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Liu et al., 2019] Donghua Liu, Jing Li, Bo Du, Jun Chang, and Rong Gao. DAML: dual attention mutual learning between ratings and reviews for item recommendation. In KDD, pages 344-352, 2019.","title":"DAML: dual attention mutual learning between ratings and reviews for item recommendation","authors":"Donghua Liu, Jing Li, Bo Du, Jun Chang, Rong Gao","year":"2019","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2020] Hui Liu, Zhan Shi, Jia-Chen Gu, Quan Liu, Si Wei, and Xiaodan Zhu. End-to-end transition-based online dialogue disentanglement. In IJCAI, pages 3868- 3874, 7 2020.","title":"End-to-end transition-based online dialogue disentanglement","authors":"Hui Liu, Zhan Shi, Jia-Chen Gu, Quan Liu, Si Wei, Xiaodan Zhu","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/535"},{"position":12,"raw":"[Liu et al., 2021] Hui Liu, Zhan Shi, and Xiaodan Zhu. Unsupervised conversation disentanglement through co- training. In EMNLP, pages 2345-2356, 2021.","title":"Unsupervised conversation disentanglement through cotraining","authors":"Hui Liu, Zhan Shi, Xiaodan Zhu","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mehri and Carenini, 2017] Shikib Mehri and Giuseppe Carenini. Chat disentanglement: Identifying semantic re- ply relationships with random forests and recurrent neural networks. In IJCNLP, pages 615-623, 2017.","title":"Shikib Mehri and Giuseppe Carenini. Chat disentanglement: Identifying semantic reply relationships with random forests and recurrent neural networks","authors":"Carenini Mehri","year":"2017","venue":"IJCNLP","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nguyen et al., 2020] Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq R. Joty, and Xiaoli Li. Efficient con- stituency parsing by pointing. In ACL, pages 3284-3294, 2020.","title":"Efficient constituency parsing by pointing","authors":"Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq R Joty, Xiaoli Li","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pappadopulo et al., 2021] Duccio Pappadopulo, Lisa Bauer, Marco Farina, Ozan Irsoy, and Mohit Bansal. Disentan- gling online chats with dag-structured lstms. In *SEM, pages 152-159, 2021.","title":"Disentangling online chats with dag-structured lstms","authors":"Pappadopulo","year":"2021","venue":"SEM","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Qu et al., 2018] Chen Qu, Liu Yang, W. Bruce Croft, Jo- hanne R. Trippas, Yongfeng Zhang, and Minghui Qiu. Analyzing and characterizing user intent in information- seeking conversations. In SIGIR, pages 989-992, 2018.","title":"Analyzing and characterizing user intent in informationseeking conversations","authors":"Chen Qu, Liu Yang, W Bruce Croft, Johanne R Trippas, Yongfeng Zhang, Minghui Qiu","year":"2018","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Santos and Embrechts, 2009] Jorge M. Santos and Mark J. Embrechts. On the use of the adjusted rand index as a metric for evaluating supervised classification. In ICANN, volume 5769, pages 175-184, 2009.","title":"On the use of the adjusted rand index as a metric for evaluating supervised classification","authors":"Jorge M Santos, Mark J Embrechts","year":"2009","venue":"ICANN","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Severyn and Moschitti, 2015] Aliaksei Severyn and Alessandro Moschitti. Learning to rank short text pairs with convolutional deep neural networks. In SIGIR, pages 373-382, 2015.","title":"Learning to rank short text pairs with convolutional deep neural networks","authors":"Aliaksei Severyn, Alessandro Moschitti","year":"2015","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shen et al., 2006] Dou Shen, Qiang Yang, Jian-Tao Sun, and Zheng Chen. Thread detection in dynamic text mes- sage streams. In SIGIR, pages 35-42, 2006.","title":"Thread detection in dynamic text message streams","authors":"Dou Shen, Qiang Yang, Jian-Tao Sun, Zheng Chen","year":"2006","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Strehl and Ghosh, 2002] Alexander Strehl and Joydeep Ghosh. Cluster ensembles -A knowledge reuse frame- work for combining multiple partitions. J. Mach. Learn. Res., 3:583-617, 2002.","title":"Cluster ensembles -A knowledge reuse framework for combining multiple partitions","authors":"Ghosh Strehl, Alexander Strehl, Joydeep Ghosh","year":"2002","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tan et al., 2019] Ming Tan, Dakuo Wang, Yupeng Gao, Haoyu Wang, Saloni Potdar, Xiaoxiao Guo, Shiyu Chang, and Mo Yu. Context-aware conversation thread detec- tion in multi-party chat. In EMNLP-IJCNLP, pages 6455- 6460, 2019.","title":"Context-aware conversation thread detection in multi-party chat","authors":"Ming Tan, Dakuo Wang, Yupeng Gao, Haoyu Wang, Saloni Potdar, Xiaoxiao Guo, Shiyu Chang, Mo Yu","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu et al., 2019] Runmin Wu, Mengyang Feng, Wenlong Guan, Dong Wang, Huchuan Lu, and Errui Ding. A mu- tual learning method for salient object detection with in- tertwined multi-supervision. In CVPR, pages 8150-8159, 2019.","title":"A mutual learning method for salient object detection with intertwined multi-supervision","authors":"Wu","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yang et al., 2016] Zichao Yang, Diyi Yang, Chris Dyer, Xi- aodong He, Alex Smola, and Eduard Hovy. Hierarchical attention networks for document classification. In NAACL, pages 1480-1489, 2016.","title":"Hierarchical attention networks for document classification","authors":"Yang","year":"2016","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2020] Taojiannan Yang, Sijie Zhu, Chen Chen, Shen Yan, Mi Zhang, and Andrew R. Willis. Mutualnet: Adaptive convnet via mutual learning from network width and resolution. In ECCV, volume 12346 of Lecture Notes in Computer Science, pages 299-315, 2020.","title":"Mutualnet: Adaptive convnet via mutual learning from network width and resolution","authors":"Taojiannan Yang, Sijie Zhu, Chen Chen, Shen Yan, Mi Zhang, Andrew R Willis","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yin et al., 2016] Wenpeng Yin, Hinrich Schütze, Bing Xi- ang, and Bowen Zhou. ABCNN: attention-based convolu- tional neural network for modeling sentence pairs. Trans. Assoc. Comput. Linguistics, 4:259-272, 2016.","title":"ABCNN: attention-based convolutional neural network for modeling sentence pairs","authors":"Yin","year":"2016","venue":"Trans. Assoc. Comput. Linguistics","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yu and Joty, 2020] Tao Yu and Shafiq R. Joty. Online conversation disentanglement with pointer networks. In EMNLP, pages 6321-6330, 2020.","title":"Online conversation disentanglement with pointer networks","authors":"Tao Yu, Shafiq R Joty","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2018] Ying Zhang, Tao Xiang, Timothy M. Hospedales, and Huchuan Lu. Deep mutual learning. In CVPR, pages 4320-4328, 2018.","title":"Deep mutual learning","authors":"Ying Zhang, Tao Xiang, Timothy M Hospedales, Huchuan Lu","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhu et al., 2021] Rongxin Zhu, Jey Han Lau, and Jianzhong Qi. Findings on conversation disentanglement. arXiv preprint arXiv:2112.05346, 2021.","title":"Findings on conversation disentanglement","authors":"Rongxin Zhu, Jey Han Lau, Jianzhong Qi","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}