Abstract
Dialogue State Tracking (DST) aims to keep dialogue states updated over the whole dialogue. Recently, slot self-attention mechanism and token-level schema graph are both proposed to capture slot relations based on prior knowledge or human experience, avoiding the independent prediction of slot values. However, they fall short in modeling the correlations among slots across domain, and the dialogue history encoding method injects noises into the slot representations. To address these issues, we propose a novel slot-level schema graph to involve high cooccurrence slot relations across domain. A two layers network is then adopted to force slots to pay attention only on the relevant dialogue context and related slots successively. We make a further comparison study in modeling slot relation to quantify that the improvement of our schema graph is superior to slot self-attention. Empirical results on benchmark datasets (i.e., MultiWOZ 2.0, MultiWOZ 2.1, and MultiWOZ 2.4) show that our approach outperforms strong baselines in both predefined ontology-based DST and open vocabulary-based DST methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lee, H., Lee, J., Kim, T.: SUMBT: slot-utterance matching for universal and scalable belief tracking. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5478–5483. Association for Computational Linguistics, Florence, Italy (2019)
Wu, C.S., Madotto, A., Hosseini-Asl, E., Xiong, C., Socher, R., Fung, P.: Transferable multi-domain state generator for task-oriented dialogue systems. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 808–819. Association for Computational Linguistics, Florence, Italy (2019)
Kim, S., Yang, S., Kim, G., Lee, S.: Efficient dialogue state tracking by selectively overwriting memory. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 567–582. Association for Computational Linguistics, Online (2020)
Heck, M., et al.: TripPy: a triple copy strategy for value independent neural dialog state tracking. In: Proceedings of the 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 35–44. Association for Computational Linguistics, 1st virtual meeting (2020)
Ye, F., Manotumruksa, J., Zhang, Q., Li, S., Yilmaz, E.: Slot self-attentive dialogue state tracking. In: The Web Conference (WWW), pp. 1598–1608. New York, USA (2021)
Wang, Y., Zhao, J., Bao, J., Duan, C., Wu, Y., He, X.: LUNA: learning slot-turn alignment for dialogue state tracking. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3319–3328. Association for Computational Linguistics, Seattle, United States (2022)
Zhou, Y., Zhao, G., Qian, X.: Dialogue state tracking based on hierarchical slot attention and contrastive learning. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 4737–4741 (2022)
Zhu, S., Li, J., Chen, L., Yu, K.: Efficient context and schema fusion networks for multi-domain dialogue state tracking. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 766–781. Association for Computational Linguistics, Online (2020)
Chen, L., Lv, B., Wang, C., Zhu, S., Tan, B., Yu, K.: Schema-guided multi-domain dialogue state tracking with graph attention neural networks. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, pp. 7521–7528. AAAI Press (2020)
Lin, W., Tseng, B.H., Byrne, B.: Knowledge-aware graph-enhanced GPT-2 for dialogue state tracking. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7871–7881. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021)
Wang, Z., Lemon, O.: A simple and generic belief tracking mechanism for the dialog state tracking challenge: On the believability of observed information. In: Proceedings of the SIGDIAL 2013 Conference, pp. 423–432. Association for Computational Linguistics, Metz, France (2013)
Henderson, M., Thomson, B., Young, S.: Word-based dialog state tracking with recurrent neural networks. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 292–299. Association for Computational Linguistics, Philadelphia, PA, U.S.A. (2014)
Mrkšić, N., Ó Séaghdha, D., Wen, T.H., Thomson, B., Young, S.: Neural belief tracker: data-driven dialogue state tracking. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1777–1788. Association for Computational Linguistics, Vancouver, Canada (2017)
Nouri, E., Hosseini-Asl, E.: Toward scalable neural dialogue state tracking. In: NeurIPS 2018, 2nd Conversational AI workshop (2018)
Ouyang, Y., Chen, M., Dai, X., Zhao, Y., Huang, S., Chen, J.: Dialogue state tracking with explicit slot connection modeling. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 34–40. Association for Computational Linguistics, Online (2020)
Ren, L., Xie, K., Chen, L., Yu, K.: Towards universal dialogue state tracking. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2780–2786. Association for Computational Linguistics, Brussels, Belgium (2018)
Shan, Y., et al.: A contextual hierarchical attention network with adaptive objective for dialogue state tracking. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6322–6333. Association for Computational Linguistics, Online (2020)
Wu, C.S., Hoi, S.C., Socher, R., Xiong, C.: TOD-BERT: pre-trained natural language understanding for task-oriented dialogue. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 917–929. Association for Computational Linguistics, Online (2020)
Ham, D., Lee, J.G., Jang, Y., Kim, K.E.: End-to-end neural pipeline for goal-oriented dialogue systems using GPT-2. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online (2020)
Hosseini-Asl, E., McCann, B., Wu, C.S., Yavuz, S., Socher, R.: A simple language model for task-oriented dialogue. Adv. Neural Inf. Process. Syst. 33, 20179–20191 (2020)
Hu, J., Yang, Y., Chen, C., He, L., Yu, Z.: SAS: dialogue state tracking via slot attention and slot information sharing. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6366–6375. Association for Computational Linguistics, Online (2020)
Yang, L., Li, J., Li, S., Shinozaki, T.: Multi-domain dialogue state tracking with top-k slot self attention. In: Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 231–236 (2022)
Wu, P., Zou, B., Jiang, R., Aw, A.: GCDST: a graph-based and copy-augmented multi-domain dialogue state tracking. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1063–1073. Association for Computational Linguistics, Online (2020)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. vol. 30 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, J., Song, H., Xu, B., Zhou, H. (2023). Dialogue State Tracking with a Dialogue-Aware Slot-Level Schema Graph Approach. In: Jin, Z., Jiang, Y., Buchmann, R.A., Bi, Y., Ghiran, AM., Ma, W. (eds) Knowledge Science, Engineering and Management. KSEM 2023. Lecture Notes in Computer Science(), vol 14119. Springer, Cham. https://doi.org/10.1007/978-3-031-40289-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-40289-0_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40288-3
Online ISBN: 978-3-031-40289-0
eBook Packages: Computer ScienceComputer Science (R0)