Liqiang Song
ABSTRACT
Different from traditional task-oriented and open-domain dialogue systems, insurance agents aim to engage customers for helping them satisfy specific demands and emotional companionship. As a result, customer-to-agent dialogues are usually very long, and many turns of them are pure chit-chat without any useful marketing clues. This brings challenges to dialogue state tracking task in insurance marketing. To deal with these long and sparse dialogues, we propose a new dialogue state tracking architecture containing three components: dialogue encoder, Smart History Collector (SHC) and dialogue state classifier. SHC, a deliberately designed memory network, effectively selects relevant dialogue history via slot-attention, and then updates dialogue history memory. With SHC, our model is able to keep track of the vital information and filter out pure chit-chat. Experimental results demonstrate that our proposed LS-DST significantly outperforms the state-of-the-art baselines on real insurance dialogue dataset.
Supplemental Material
- L.J. Ba, J. R. Kiros, and G.E. Hinton. 2016. Layer Normalization. CoRR, Vol. abs/1607.06450 (2016).Google Scholar
- P. Budzianowski, T.H. Wen, B.H. Tseng, I. Casanueva, S. Ultes, O. Ramadan, and M. Gasic. 2018. MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling. In EMNLP. 5016--5026.Google Scholar
- L. Chen, B. Lv, C. Wang, S. Zhu, B. Tan, and K. Yu. 2020. Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks. In AAAI. 7521--7528.Google Scholar
- J. Devlin, M.W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In ACL. 4171--4186.Google Scholar
- M. Eric, R. Goel, S. Paul, A. Sethi, S. Agarwal, S. Gao, A. Kumar, A.K. Goyal, P. Ku, and D. Hakkani-Tür. 2020. MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines. In LREC. 422--428.Google Scholar
- S. Kim, S. Yang, G. Kim, and S.W. Lee. 2020. Efficient Dialogue State Tracking by Selectively Overwriting Memory. In ACL. 567--582.Google Scholar
- H. Le, D. Sahoo, C. Liu, N.F. Chen, and S.C.H. Hoi. 2020. End-to-end multi-domain task-oriented dialogue systems with multi-level neural belief tracker. In ICLR .Google Scholar
- H. Lee, J. Lee, and T.Y. Kim. 2019. SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking. In ACL. 5478--5483.Google Scholar
- N. Mrksic, D. Ó Séaghdha, T.H. Wen, B. Thomson, and S.J. Young. 2017. Neural Belief Tracker: Data-Driven Dialogue State Tracking. In ACL. 1777--1788.Google Scholar
- O. Ramadan, P. Budzianowski, and M. Gasic. 2018. Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing. In ACL. 432--437.Google Scholar
- L. Ren, J. Ni, and J.J. McAuley. 2019. Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation. In EMNLP. 1876--1885.Google Scholar
- J.D. Williams and S.J. Young. 2007. Partially observable Markov decision processes for spoken dialog systems. Comput. Speech Lang., Vol. 21, 2 (2007), 393--422.Google ScholarDigital Library
- C.S. Wu, A. Madotto, E. Hosseini-Asl, C. Xiong, R. Socher, and P. Fung. 2019. Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems. In ACL. 808--819.Google Scholar
- V. Zhong, C. Xiong, and R. Socher. 2018. Global-Locally Self-Attentive Encoder for Dialogue State Tracking. In ACL. 1458--1467.Google Scholar
Index Terms
- LS-DST: Long and Sparse Dialogue State Tracking with Smart History Collector in Insurance Marketing
Recommendations
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 ...
Explicit State Tracking with Semi-Supervisionfor Neural Dialogue Generation
CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge ManagementThe task of dialogue generation aims to automatically provide responses given previous utterances. Tracking dialogue states is an important ingredient in dialogue generation for estimating users' intention. However, the expensive nature of state ...
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 ...
Comments