{"type":"ScholarlyArticle","title":"On Tracking Dialogue State by Inheriting Slot Values in Mentioned Slot Pools","authors":[{"name":"Zhoujian Sun","slug":"zhoujian-sun","given":"Zhoujian","family":"Sun","affiliation":"Zhejiang University"},{"name":"Zhengxing Huang","slug":"zhengxing-huang","given":"Zhengxing","family":"Huang","affiliation":"Zhejiang University"},{"name":"Nai Ding","slug":"nai-ding","given":"Nai","family":"Ding","affiliation":"Zhejiang University"}],"abstract":"Dialogue state tracking (DST) is a component of the task oriented dialogue system. It is responsible for extracting and managing slots, where each slot represents a part of the information to accomplish a task, and slot value is updated recurrently in each dialogue turn. However, many DST models cannot update slot values appropriately. These models may repeatedly inherit wrong slot values extracted in previous turns, resulting in the fail of the entire DST task. They cannot update indirectly mentioned slots well, either. This study designed a model with a mentioned slot pool (MSP) to tackle the update problem. The MSP is a slot specific memory that records all mentioned slot values that may be inherited, and our model updates slot values according to the MSP and the dialogue context. Our model rejects inheriting the previous slot value when it predicates the value is wrong. Then, it extracts the slot value from the current dialogue context. As the contextual information accumulates, the new value is more likely to be correct. It also can track the indirectly mentioned slot by picking a value from the MSP. Experimental results showed our model reached state of the art DST performance on MultiWOZ datasets.","doi":"10.24963/ijcai.2022/607","url":"https://ijcai.org/proceedings/2022/607","pdf":"https://ijcai.org/proceedings/2022/0607.pdf","markdown":"https://ijcai.org/proceedings/2022/607.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/607","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":607,"pages":{"first":4375,"last":4382},"keywords":["Natural Language Processing: Dialogue and Interactive Systems","Natural Language Processing: Natural Language Semantics"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986551","length_sec":75,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984694","length_sec":339,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chao and Lane, 2019] Guan-Lin Chao and Ian Lane. BERT-DST: Scalable end-to-end dialogue state track- ing with bidirectional encoder representations from transformer. In INTERSPEECH, 2019.","title":"BERT-DST: Scalable end-to-end dialogue state tracking with bidirectional encoder representations from transformer","authors":"Guan-Lin Chao, Ian Lane","year":"2019","venue":"INTERSPEECH","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 Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171-4186, June 2019.","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Devlin","year":"2019","venue":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Eric et al., 2020] Mihail Eric, Rahul Goel, Shachi Paul, Ab- hishek Sethi, Sanchit Agarwal, Shuyang Gao, Adarsh Ku- mar, Anuj Goyal, Peter Ku, and Dilek Hakkani-Tur. Mul- tiWOZ 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines. In Pro- ceedings of the 12th Language Resources and Evaluation Conference, pages 422-428, May 2020.","title":"Mul-tiWOZ 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines","authors":"Mihail Eric, Rahul Goel, Shachi Paul, Abhishek Sethi, Sanchit Agarwal, Shuyang Gao, Adarsh Kumar, Anuj Goyal, Peter Ku, Dilek Hakkani-Tur","year":"2020","venue":"Proceedings of the 12th Language Resources and Evaluation Conference","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Feng et al., 2021] Yue Feng, Yang Wang, and Hang Li. A sequence-to-sequence approach to dialogue state tracking. In Proceedings of the 59th Annual Meeting of the Associ- ation for Computational Linguistics and the 11th Interna- tional Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1714-1725, August 2021.","title":"A sequence-to-sequence approach to dialogue state tracking","authors":"Yue Feng, Yang Wang, Hang Li","year":"2021","venue":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2019] Shuyang Gao, Abhishek Sethi, Sanchit Agarwal, Tagyoung Chung, and Dilek Hakkani-Tur. Di- alog state tracking: A neural reading comprehension ap- proach. In Proceedings of the 20th Annual SIGdial Meet- ing on Discourse and Dialogue, pages 264-273, Septem- ber 2019.","title":"Dialog state tracking: A neural reading comprehension approach","authors":"Shuyang Gao, Abhishek Sethi, Sanchit Agarwal, Tagyoung Chung, Dilek Hakkani-Tur","year":"2019","venue":"Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Heck et al., 2020] Michael Heck, Carel van Niekerk, Nu- rul Lubis, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, and Milica Gasic. Trippy: A triple copy strategy for value independent neural dialog state tracking. In Pro- ceedings of the 21th Annual Meeting of the Special Inter- est Group on Discourse and Dialogue, pages 35-44, July 2020.","title":"Trippy: A triple copy strategy for value independent neural dialog state tracking","authors":"Michael Heck, Nurul Carel Van Niekerk, Christian Lubis, Hsien-Chin Geishauser, Marco Lin, Milica Moresi, Gasic","year":"2020","venue":"Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hosseini-Asl et al., 2020] Ehsan Hosseini-Asl, Bryan Mc- Cann, Chien-Sheng Wu, Semih Yavuz, and Richard Socher. A simple language model for task-oriented dia- logue. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin, editors, Advances in Neural Informa- tion Processing Systems, volume 33, pages 20179-20191, 2020.","title":"A simple language model for task-oriented dialogue","authors":"Ehsan Hosseini-Asl, Bryan Mc-Cann, Chien-Sheng Wu, Semih Yavuz, Richard Socher","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kim et al., 2018] Jin-Hwa Kim, Jaehyun Jun, and Byoung- Tak Zhang. Bilinear attention networks. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS'18, page 1571-1581, 2018.","title":"Bilinear attention networks","authors":"Jin-Hwa Kim, Jaehyun Jun, Byoung-Tak Zhang","year":"2018","venue":"Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS'18","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kim et al., 2020] Sungdong Kim, Sohee Yang, Gyuwan Kim, and Sang-Woo Lee. Efficient dialogue state track- ing by selectively overwriting memory. In Proceedings of the 58th Annual Meeting of the Association for Computa- tional Linguistics, pages 567-582, July 2020.","title":"Efficient dialogue state tracking by selectively overwriting memory","authors":"Kim","year":"2020","venue":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kingma and Ba, 2015] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. Interna- tional Conference on Learning Representations, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lee et al., 2019] Hwaran Lee, Jinsik Lee, and Tae-Yoon Kim. SUMBT: Slot-utterance matching for universal and scalable belief tracking. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5478-5483, July 2019.","title":"SUMBT: Slot-utterance matching for universal and scalable belief tracking","authors":"Lee","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2021] Shiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Rajani, Xifeng Yan, Yingbo Zhou, and Caiming Xiong. Coco: Control- lable counterfactuals for evaluating dialogue state trackers. International Conference on Learning Representations, 2021.","title":"Coco: Controllable counterfactuals for evaluating dialogue state trackers","authors":"Shiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Rajani, Xifeng Yan, Yingbo Zhou, Caiming Xiong","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2021] Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586, 2021.","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","authors":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, Graham Neubig","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Manotumruksa et al., 2021] Jarana Manotumruksa, Jeff Dalton, Edgar Meij, and Emine Yilmaz. Improving dialogue state tracking with turn-based loss function and sequential data augmentation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1674-1683, November 2021.","title":"Improving dialogue state tracking with turn-based loss function and sequential data augmentation","authors":"Jarana Manotumruksa, Jeff Dalton, Edgar Meij, Emine Yilmaz","year":"2021","venue":"Findings of the Association for Computational Linguistics: EMNLP 2021","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mehri et al., 2020] S. Mehri, M. Eric, and D. Hakkani- Tur. Dialoglue: A natural language understanding benchmark for task-oriented dialogue. arXiv preprint arXiv:2009.13570, 2020.","title":"Dialoglue: A natural language understanding benchmark for task-oriented dialogue","authors":"S Mehri, M Eric, D Hakkani-Tur","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ni et al., 2021] Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Vinay Adiga, and Erik Cambria. Recent ad- vances in deep learning-based dialogue systems. arXiv preprint arXiv:2105.04387, 2021.","title":"Recent advances in deep learning-based dialogue systems","authors":"Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Vinay Adiga, Erik Cambria","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nouri and Hosseini-Asl, 2018] Elnaz Nouri and Ehsan Hosseini-Asl. Toward scalable neural dialogue state tracking. In NeurIPS 2018, 2nd Conversational AI workshop, 2018.","title":"Toward scalable neural dialogue state tracking","authors":"Elnaz Nouri, Ehsan Hosseini-Asl","year":"2018","venue":"NeurIPS 2018, 2nd Conversational AI workshop","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Song et al., 2021] Xiaohui Song, Liangjun Zang, and Songlin Hu. Data augmentation for copy-mechanism in dialogue state tracking. In International Conference on Computational Science, pages 736-749. Springer, 2021.","title":"Data augmentation for copy-mechanism in dialogue state tracking","authors":"Xiaohui Song, Liangjun Zang, Songlin Hu","year":"2021","venue":"International Conference on Computational Science","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Summerville et al., 2020] Adam Summerville, Jordan Hashemi, James Ryan, and William Ferguson. How to tame your data: Data augmentation for dialog state tracking. In Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, pages 32-37, July 2020.","title":"How to tame your data: Data augmentation for dialog state tracking","authors":"Adam Summerville, Jordan Hashemi, James Ryan, William Ferguson","year":"2020","venue":"Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tian et al., 2021] Xin Tian, Liankai Huang, Yingzhan Lin, Siqi Bao, Huang He, Yunyi Yang, Hua Wu, Fan Wang, and Shuqi Sun. Amendable generation for dialogue state tracking. In Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pages 80-92, November 2021.","title":"Amendable generation for dialogue state tracking","authors":"Xin Tian, Liankai Huang, Yingzhan Lin, Siqi Bao, Huang He, Yunyi Yang, Hua Wu, Fan Wang, Shuqi Sun","year":"2021","venue":"Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Townsend et al., 2001] David J Townsend, Thomas G Bever, Thomas G Bever, et al. Sentence comprehension: The integration of habits and rules. MIT Press, 2001.","title":"Sentence comprehension: The integration of habits and rules","authors":"J David, Thomas G Townsend, Thomas G Bever, Bever","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wen et al., 2017] Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gašić, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. A network- based end-to-end trainable task-oriented dialogue system. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 438-449, April 2017.","title":"A networkbased end-to-end trainable task-oriented dialogue system","authors":"Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gašić, Lina M Rojas-Barahona, Pei-Hao Su, Stefan Ultes, Steve Young","year":"2017","venue":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2016] Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, et al. Google's neural machine translation sys- tem: Bridging the gap between human and machine trans- lation. arXiv preprint arXiv:1609.08144, 2016.","title":"Google's neural machine translation system: Bridging the gap between human and machine translation","authors":"Yonghui Wu, Mike Schuster, Zhifeng Chen, V Quoc, Mohammad Le, Wolfgang Norouzi, Maxim Macherey, Yuan Krikun, Qin Cao, Klaus Gao, Macherey","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2019] Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, and Pas- cale Fung. Transferable multi-domain state generator for task-oriented dialogue systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Lin- guistics (Volume 1: Long Papers), 2019.","title":"Transferable multi-domain state generator for task-oriented dialogue systems","authors":"Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, Pascale Fung","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zang et al., 2020] Xiaoxue Zang, Abhinav Rastogi, Srini- vas Sunkara, Raghav Gupta, Jianguo Zhang, and Jindong Chen. MultiWOZ 2.2 : A dialogue dataset with additional annotation corrections and state tracking baselines. In Pro- ceedings of the 2nd Workshop on Natural Language Pro- cessing for Conversational AI, pages 109-117, July 2020.","title":"MultiWOZ 2.2 : A dialogue dataset with additional annotation corrections and state tracking baselines","authors":"Zang","year":"2020","venue":"Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2020] Jianguo Zhang, Kazuma Hashimoto, Chien-Sheng Wu, Yao Wang, Philip Yu, Richard Socher, and Caiming Xiong. Find or classify? dual strategy for slot-value predictions on multi-domain dialog state track- ing. In Proceedings of the Ninth Joint Conference on Lex- ical and Computational Semantics, pages 154-167, De- cember 2020.","title":"Find or classify? dual strategy for slot-value predictions on multi-domain dialog state tracking","authors":"Jianguo Zhang, Kazuma Hashimoto, Chien-Sheng Wu, Yao Wang, Philip Yu, Richard Socher, Caiming Xiong","year":"2020","venue":"Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhao et al., 2021] Jeffrey Zhao, Mahdis Mahdieh, Ye Zhang, Yuan Cao, and Yonghui Wu. Effective sequence-to-sequence dialogue state tracking. In Pro- ceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7486-7493, November 2021.","title":"Effective sequence-to-sequence dialogue state tracking","authors":"Jeffrey Zhao, Mahdis Mahdieh, Ye Zhang, Yuan Cao, Yonghui Wu","year":"2021","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhou and Small, 2019] Li Zhou and Kevin Small. Multi- domain dialogue state tracking as dynamic knowledge graph enhanced question answering. In NeurIPS Work- shop on Conversational AI, 2019.","title":"Multidomain dialogue state tracking as dynamic knowledge graph enhanced question answering","authors":"Li Zhou, Kevin Small","year":"2019","venue":"NeurIPS Workshop on Conversational AI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}