{"type":"ScholarlyArticle","title":"Dialogue State Induction Using Neural Latent Variable Models","authors":[{"name":"Qingkai Min","slug":"qingkai-min","given":"Qingkai","family":"Min","affiliation":"School of Engineering , Westlake University; Institute of Advanced Technology , Westlake Institute for Advanced Study"},{"name":"Libo Qin","slug":"libo-qin","given":"Libo","family":"Qin","affiliation":"Research Center for Social Computing and Information Retrieval , Harbin Institute of Technology"},{"name":"Zhiyang Teng","slug":"zhiyang-teng","given":"Zhiyang","family":"Teng","affiliation":"School of Engineering , Westlake University; Institute of Advanced Technology , Westlake Institute for Advanced Study"},{"name":"Xiao Liu","slug":"xiao-liu","given":"Xiao","family":"Liu","affiliation":"School of Computer Science and Technology , Beijing Institute of Technology"},{"name":"Yue Zhang","slug":"yue-zhang","given":"Yue","family":"Zhang","affiliation":"School of Engineering , Westlake University; Institute of Advanced Technology , Westlake Institute for Advanced Study"}],"abstract":"Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be costly, slow, error-prone, and more importantly, cannot cover the vast range of domains in real-world dialogues for customer service. We propose the task of dialogue state induction, building two neural latent variable models that mine dialogue states automatically from unlabeled customer service dialogue records. Results show that the models can effectively find meaningful dialogue states. In addition, equipped with induced dialogue states, a state-of-the-art dialogue system gives better performance compared with not using a dialogue state module.","doi":"10.24963/ijcai.2020/532","url":"https://ijcai.org/proceedings/2020/532","pdf":"https://ijcai.org/proceedings/2020/0532.pdf","markdown":"https://ijcai.org/proceedings/2020/532.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/532","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Natural Language Processing","track":"Main track","number":532,"pages":{"first":3845,"last":3852},"keywords":["Natural Language Processing: Dialogue"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24475/file_24475.m3u8","length_sec":294,"provider":"hls"}],"references":[{"position":1,"raw":"[Budzianowski et al., 2018] Paweł Budzianowski, Tsung- Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gašić. MultiWOZ - a large-scale multi-domain wizard-of-Oz dataset for task- oriented dialogue modelling. In EMNLP, 2018.","title":"MultiWOZa large-scale multi-domain wizard-of-Oz dataset for taskoriented dialogue modelling","authors":"Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Milica Osman Ramadan, Gašić","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2013] Yun-Nung Chen, William Yang Wang, and Alexander I Rudnicky. Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing. In ASRU Workshop, 2013.","title":"Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing","authors":"Yun-Nung Chen, William Yang, Wang, Alexander I Rudnicky","year":"2013","venue":"ASRU Workshop","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2019] Wenhu Chen, Jianshu Chen, Pengda Qin, Xifeng Yan, and William Yang Wang. Semantically con- ditioned dialog response generation via hierarchical disen- tangled self-attention. In ACL, 2019.","title":"Semantically conditioned dialog response generation via hierarchical disentangled self-attention","authors":"Chen","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cui and Zhang, 2019] Leyang Cui and Yue Zhang. Hierarchically-refined label attention network for se- quence labeling. In EMNLP, 2019.","title":"Hierarchically-refined label attention network for sequence labeling","authors":"Zhang Cui, Leyang Cui, Yue Zhang","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Eric and Manning, 2017] Mihail Eric and Christopher D Manning. A copy-augmented sequence-to-sequence archi- tecture gives good performance on task-oriented dialogue. In EACL, 2017.","title":"A copy-augmented sequence-to-sequence architecture gives good performance on task-oriented dialogue","authors":"Mihail Eric, Christopher D Manning","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Eric et al., 2019] Mihail Eric, Rahul Goel, Shachi Paul, Ab- hishek Sethi, Sanchit Agarwal, Shuyag Gao, and Dilek Hakkani-Tur. Multiwoz 2.1: Multi-domain dialogue state corrections and state tracking baselines. arXiv, 2019.","title":"Multiwoz 2.1: Multi-domain dialogue state corrections and state tracking baselines","authors":"Mihail Eric, Rahul Goel, Shachi Paul, Abhishek Sethi, Sanchit Agarwal, Shuyag Gao, Dilek Hakkani-Tur","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Goel et al., 2019] Rahul Goel, Shachi Paul, and Dilek Hakkani-Tür. Hyst: A hybrid approach for flexible and accurate dialogue state tracking. In Interspeech, 2019.","title":"Hyst: A hybrid approach for flexible and accurate dialogue state tracking","authors":"Rahul Goel, Shachi Paul, Dilek Hakkani-Tür","year":"2019","venue":"Interspeech","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hemphill et al., 1990] Charles T Hemphill, John J Godfrey, and George R Doddington. The atis spoken language sys- tems pilot corpus. In HLT, 1990.","title":"The atis spoken language systems pilot corpus","authors":"John J Charles T Hemphill, George R Godfrey, Doddington","year":"1990","venue":"HLT","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jiang et al., 2017] Zhuxi Jiang, Yin Zheng, Huachun Tan, Bangsheng Tang, and Hanning Zhou. Variational deep embedding: An unsupervised and generative approach to clustering. In IJCAI, 2017.","title":"Variational deep embedding: An unsupervised and generative approach to clustering","authors":"Jiang","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/273"},{"position":10,"raw":"[Kingma and Welling, 2014] Diederik P. Kingma and Max Welling. Auto-encoding variational bayes. In ICLR, 2014.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2014","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lei et al., 2018] Wenqiang Lei, Xisen Jin, Min-Yen Kan, Zhaochun Ren, Xiangnan He, and Dawei Yin. Sequic- ity: Simplifying task-oriented dialogue systems with sin- gle sequence-to-sequence architectures. In ACL, 2018.","title":"Sequicity: Simplifying task-oriented dialogue systems with single sequence-to-sequence architectures","authors":"Lei","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2019a] Xiao Liu, Heyan Huang, and Yue Zhang. Open domain event extraction using neural latent variable models. In ACL, 2019.","title":"Open domain event extraction using neural latent variable models","authors":"Liu","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2019b] Zihan Liu, Genta Indra Winata, Zhao- jiang Lin, Peng Xu, and Pascale Fung. Attention-informed mixed-language training for zero-shot cross-lingual task- oriented dialogue systems. In AAAI, 2019.","title":"Attention-informed mixed-language training for zero-shot cross-lingual taskoriented dialogue systems","authors":"Liu","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mrkšić et al., 2015] Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gasic, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. Multi- domain dialog state tracking using recurrent neural net- works. In ACL, 2015.","title":"Multidomain dialog state tracking using recurrent neural networks","authors":"Nikola Mrkšić, Ó Diarmuid, Blaise Séaghdha, Milica Thomson, Pei-Hao Gasic, David Su, Tsung-Hsien Vandyke, Steve Wen, Young","year":"2015","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Qin et al., 2019] Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, and Ting Liu. A stack-propagation frame- work with token-level intent detection for spoken language understanding. In EMNLP, 2019.","title":"A stack-propagation framework with token-level intent detection for spoken language understanding","authors":"Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, Ting Liu","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Qin et al., 2020] Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, and Ting Liu. Dynamic Fusion Network for Multi- Domain End-to-end Task-Oriented Dialog. arXiv, 2020.","title":"Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog","authors":"Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rastogi et al., 2019] Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, and Pranav Khaitan. Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset. In AAAI, 2019.","title":"Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset","authors":"Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, Pranav Khaitan","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ren et al., 2019] Liliang Ren, Jianmo Ni, and Julian McAuley. Scalable and accurate dialogue state tracking via hierarchical sequence generation. In EMNLP, 2019.","title":"Scalable and accurate dialogue state tracking via hierarchical sequence generation","authors":"Ren","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shi et al., 2018] Chen Shi, Qi Chen, Lei Sha, Sujian Li, Xu Sun, Houfeng Wang, and Lintao Zhang. Auto-dialabel: Labeling dialogue data with unsupervised learning. In EMNLP, 2018.","title":"Auto-dialabel: Labeling dialogue data with unsupervised learning","authors":"Chen Shi, Qi Chen, Lei Sha, Sujian Li, Xu Sun, Houfeng Wang, Lintao Zhang","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wen et al., 2017] Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gasic, Lina M Rojas Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. A network- based end-to-end trainable task-oriented dialogue system. In EACL, 2017.","title":"A networkbased end-to-end trainable task-oriented dialogue system","authors":"Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gasic, Lina M Rojas Barahona, Pei-Hao Su, Stefan Ultes, Steve Young","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wen et al., 2018] Haoyang Wen, Yijia Liu, Wanxiang Che, Libo Qin, and Ting Liu. Sequence-to-sequence learning for task-oriented dialogue with dialogue state representa- tion. In COLING, 2018.","title":"Sequence-to-sequence learning for task-oriented dialogue with dialogue state representation","authors":"Haoyang Wen, Yijia Liu, Wanxiang Che, Libo Qin, Ting Liu","year":"2018","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Williams et al., 2014] Jason D Williams, Matthew Hender- son, Antoine Raux, Blaise Thomson, Alan Black, and Deepak Ramachandran. The dialog state tracking chal- lenge series. AI Magazine, 2014.","title":"The dialog state tracking challenge series","authors":"Jason D Williams, Matthew Henderson, Antoine Raux, Blaise Thomson, Alan Black, Deepak Ramachandran","year":"2014","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2019a] Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, and Pascale Fung. Transferable multi-domain state generator for task-oriented dialogue systems. In ACL, 2019.","title":"Transferable multi-domain state generator for task-oriented dialogue systems","authors":"Wu","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2019b] Chien-Sheng Wu, Richard Socher, and Caiming Xiong. Global-to-local memory pointer networks for task-oriented dialogue. In ICLR, 2019.","title":"Global-to-local memory pointer networks for task-oriented dialogue","authors":"Wu","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xing et al., 2003] Eric P Xing, Michael I Jordan, and Stuart Russell. A generalized mean field algorithm for variational inference in exponential families. In UAI, 2003.","title":"A generalized mean field algorithm for variational inference in exponential families","authors":"Eric P Xing, Michael I Jordan, Stuart Russell","year":"2003","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Young et al., 2010] Steve Young, Milica Gašić, Simon Keizer, Franc ¸ois Mairesse, Jost Schatzmann, Blaise Thomson, and Kai Yu. The hidden information state model: A practical framework for pomdp-based spoken dialogue management. CSL, 2010.","title":"The hidden information state model: A practical framework for pomdp-based spoken dialogue management","authors":"Steve Young, Milica Gašić, Simon Keizer, Jost Franc ¸ois Mairesse, Blaise Schatzmann, Kai Thomson, Yu","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2019] Jian-Guo Zhang, Kazuma Hashimoto, Chien-Sheng Wu, Yao Wan, Philip S Yu, Richard Socher, and Caiming Xiong. Find or classify? dual strategy for slot-value predictions on multi-domain dialog state track- ing. arXiv, 2019.","title":"Find or classify? dual strategy for slot-value predictions on multi-domain dialog state tracking","authors":"Jian-Guo Zhang, Kazuma Hashimoto, Chien-Sheng Wu, Yao Wan, S Philip, Richard Yu, Caiming Socher, Xiong","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhong et al., 2018] Victor Zhong, Caiming Xiong, and Richard Socher. Global-locally self-attentive encoder for dialogue state tracking. In ACL, 2018.","title":"Global-locally self-attentive encoder for dialogue state tracking","authors":"Victor Zhong, Caiming Xiong, Richard Socher","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}