ABSTRACT
Dialogue state is a key information in traditional task-oriented dialogue systems, which represents the user's dialogue intention at each moment through a set of (slot, value). The recent methods model the slot and the dialogue context to keep track of the state, but there is a lack of refinement of context information. They do not consider the influence of dialogue context in different scenarios. Our proposed approach utilizes a fine-grained representation of each slot at multiple levels and incorporates an interaction mechanism to obtain a weight of past memory, present utterance and relevance of the slots. Besides, to address the problem that the dialogue utterance is semantically distant from the corresponding slot value, we introduce the contrastive learning to make the utterance embedding mapped under each slot name more suitable with the ground truth value and away from other slot values. This improves the accuracy of mapping between feature space and semantic space. In the predefined ontology-based approaches, our model achieves leading results with both MultiWOZ2.0 and MultiWOZ2.1 datasets.
- Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Inigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gasić. 2018. MultiWOZ--A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling. arXiv preprint arXiv:1810.00278 (2018).Google Scholar
- Junfan Chen, Richong Zhang, Yongyi Mao, and Jie Xu. 2020. Parallel interactive networks for multi-domain dialogue state generation. arXiv preprint arXiv:2009.07616 (2020).Google Scholar
- Lu Chen, Boer Lv, Chi Wang, Su Zhu, Bowen Tan, and Kai Yu. 2020. Schemaguided multi-domain dialogue state tracking with graph attention neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 7521--7528.Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).Google Scholar
- Mihail Eric, Rahul Goel, Shachi Paul, Abhishek Sethi, Sanchit Agarwal, Shuyang Gao, and Dilek Hakkani-Tür. 2019. Multiwoz 2.1: Multi-domain dialogue state corrections and state tracking baselines. (2019).Google Scholar
- Jinyu Guo, Kai Shuang, Jijie Li, and Zihan Wang. 2021. Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking. arXiv preprint arXiv:2107.12578 (2021).Google Scholar
- Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9729--9738.Google ScholarCross Ref
- Michael Heck, Carel van Niekerk, Nurul Lubis, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, and Milica Gasic. 2020. Trippy: A triple copy strategy for value independent neural dialog state tracking. arXiv preprint arXiv:2005.02877 (2020).Google Scholar
- Sungdong Kim, Sohee Yang, Gyuwan Kim, and Sang-Woo Lee. 2019. Efficient dialogue state tracking by selectively overwriting memory. arXiv preprint arXiv:1911.03906 (2019).Google Scholar
- Hwaran Lee, Jinsik Lee, and Tae-Yoon Kim. 2019. Sumbt: Slot-utterance matching for universal and scalable belief tracking. arXiv preprint arXiv:1907.07421 (2019).Google Scholar
- Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, and Xianchao Zhang. 2021. An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling. In Findings of the Association for Computational Linguistics: EMNLP 2021. 1945--1955.Google Scholar
- Liliang Ren, Jianmo Ni, and Julian McAuley. 2019. Scalable and accurate dialogue state tracking via hierarchical sequence generation. arXiv preprint arXiv:1909.00754 (2019).Google Scholar
- Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu, and Jie Zhou. 2020. A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking. CoRR abs/2006.01554 (2020). arXiv:2006.01554 https://arxiv.org/abs/2006.01554Google Scholar
- Hao Tang, Guoshuai Zhao, Yuxia Wu, and Xueming Qian. 2021. Multisamplebased Contrastive Loss for Top-k Recommendation. IEEE Transactions on Multimedia (2021), 1--1. https://doi.org/10.1109/TMM.2021.3126146Google Scholar
- Aaron Van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv e-prints (2018), arXiv--1807.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).Google Scholar
- Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, and Pascale Fung. 2019. Transferable multi-domain state generator for task-oriented dialogue systems. arXiv preprint arXiv:1905.08743 (2019).Google Scholar
- YuxiaWu, Lizi Liao, Gangyi Zhang,Wenqiang Lei, Guoshuai Zhao, Xueming Qian, and Tat-Seng Chua. 2022. State Graph Reasoning for Multimodal Conversational Recommendation. IEEE Transactions on Multimedia (2022), 1--1. https://doi.org/10.1109/TMM.2022.3155900Google ScholarDigital Library
- Fanghua Ye, Jarana Manotumruksa, Qiang Zhang, Shenghui Li, and Emine Yilmaz. 2021. Slot Self-Attentive Dialogue State Tracking. In Proceedings of the Web Conference 2021. 1598--1608.Google ScholarDigital Library
- Xuanzhi Zheng, Guoshuai Zhao, Li Zhu, Jihua Zhu, and Xueming Qian. 2022. What You Like, What I Am: Online Dating Recommendation via Matching Individual Preferences with Features. IEEE Transactions on Knowledge and Data Engineering (2022), 1--1. https://doi.org/10.1109/TKDE.2022.3148485Google ScholarDigital Library
- Jingyao Zhou, Haipang Wu, Zehao Lin, Guodun Li, and Yin Zhang. 2021. Dialogue state tracking with multi-level fusion of predicted dialogue states and conversations. arXiv preprint arXiv:2107.05168 (2021).Google Scholar
Index Terms
- Dialogue State Tracking Based on Hierarchical Slot Attention and Contrastive Learning
Recommendations
Toward Real-life Dialogue State Tracking Involving Negative Feedback Utterances
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningRecently, the research of dialogue systems has been widely concerned, especially task-oriented dialogue systems, which have received increased attention due to their wide application prospect. As a core component, dialogue state tracking (DST) plays a ...
Slot Self-Attentive Dialogue State Tracking
WWW '21: Proceedings of the Web Conference 2021An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users’ intentions in the course of conversation. The typical approach towards this goal is to fill in multiple pre-defined slots that are ...
Hierarchical temporal slot interactions for dialogue state tracking
AbstractDialogue state tracking (DST), as an essential component of task-oriented dialogue systems, refers to keeping track of the user’s intentions as a conversation progresses. Typical methods formulate it as a classification task with fixed pre-defined ...
Comments