Abstract
Task-oriented dialogue systems are very important due to their wide range of applications. In particular, those tasks that involve multiple domains have gained increasing attention in recent years, as the actual tasks performed by virtual assistants often span multiple domains. In this work, we propose the Divide-and-Conquer Distributed Architecture with Slot Sharing Mechanism (DCDA-S2M) system, which includes not only a distributed system aimed at managing dialogues through the pipeline architecture, but also a slot sharing mechanism that allows the system to obtain information during a conversation in one domain and reuse it in another domain, in order to avoid redundant interactions and make the dialogue more efficient. Results show that the distributed architecture outperforms the centralized one by 21.51% and that the slot sharing mechanism improves the system performance both in the success rate and in the number of turns during the dialogue, demonstrating that it can prevent the agent from requesting redundant information.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
MultiWOZ is a fully-labeled collection of human-human written conversations spanning over multiple domains and topics – https://github.com/budzianowski/multiwoz.
- 2.
References
Ahmed, A., Shervashidze, N., Narayanamurthy, S., Josifovski, V., Smola, A.J.: Distributed large-scale natural graph factorization. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 37–48 (2013)
Bordes, A., Weston, J.: Learning end-to-end goal-oriented dialog. In: 2017 International Conference on Learning Representations (ICLR) (2017)
Chen, L., Chen, Z., Tan, B., Long, S., Gasic, M., Yu, K.: AgentGraph: towards universal dialogue management with structured deep reinforcement learning. ArXiv:abs/1905.11259 (2019)
Cuayáhuitl, H., Yu, S., Williamson, A., Carse, J.: Scaling up deep reinforcement learning for multi-domain dialogue systems. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 3339–3346 (2017)
Dai, Y., Yu, H., Jiang, Y., Tang, C., Li, Y., Sun, J.: A survey on dialog management: recent advances and challenges. ArXiv:abs/2005.02233 (2020)
Gao, J., Galley, M., Li, L.: Neural approaches to conversational AI. Found. Trends® Inf. Retr. 13, 127–298 (2019)
Gordon-Hall, G., Gorinski, P.J., Cohen, S.B.: Learning dialog policies from weak demonstrations. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1394–1405 (July 2020)
Gordon-Hall, G., Gorinski, P.J., Lampouras, G., Iacobacci, I.: Show us the way: learning to manage dialog from demonstrations. ArXiv:abs/2004.08114 (2020)
Ilievski, V., Musat, C., Hossmann, A., Baeriswyl, M.: Goal-oriented chatbot dialog management bootstrapping with transfer learning. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (2018)
Kim, Y., Lee, S., Stratos, K.: ONENET: joint domain, intent, slot prediction for spoken language understanding. In: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 547–553 (2017)
Komatani, K., et al.: Multi-domain spoken dialogue system with extensibility and robustness against speech recognition errors. In: Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue, pp. 9–17 (July 2006)
Li, X., Chen, Y.N., Li, L.: End-to-end task-completion neural dialogue system. In: Proceedings of the The 8th International Joint Conference on Natural Language Processing, pp. 733–743 (2017)
Peng, B., Li, X., Gao, J., Liu, J., Wong, K.F., Su, S.Y.: Deep Dyna-Q: integrating planning for task-completion dialogue policy learning. In: ACL (2018)
Peng, B., et al.: Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2231–2240 (2017)
Saha, T., Gupta, D., Saha, S., Bhattacharyya, P.: Towards integrated dialogue policy learning for multiple domains and intents using hierarchical deep reinforcement learning. Expert Syst. Appl. 162, 113650 (2020)
Schatzmann, J., Young, S.: The hidden agenda user simulation model. IEEE Trans. Audio Speech Lang. Process. 17, 733–747 (2009)
Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. ArXiv:abs/1506.02438 (2015)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. ArXiv:abs/1707.06347 (2017)
Serban, I.V., Sordoni, A., Benggio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 3776–3783 (2016)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Vlasov, V., Drissner-Schmid, A., Nichol, A.: Few-shot generalization across dialogue tasks. CoRR:abs/1811.11707 (2018)
Vlasov, V., Mosig, J.E.M., Nichol, A.: Dialogue transformers. ArXiv:abs/1910.00486 (2019)
Wang, Z., Chen, H., Wang, G., Tian, H., Wu, H., Wang, H.: Policy learning for domain selection in an extensible multi-domain spoken dialogue system. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 57–67, Doha, Qatar (October 2014)
Zhang, Z., Takanobu, R., Zhu, Q., Huang, M., Zhu, X.: Recent advances and challenges in task-oriented dialog system. Sci. China Technol. Sci. 63, 2011–2027 (2020)
Zhu, Q., et al.: ConvLab-2: an open-source toolkit for building, evaluating, and diagnosing dialogue systems. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
Acknowledgments
The authors acknowledge the support from the Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq grant 310085/2020-9), the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES Finance Code 001), and from Itaú Unibanco, through the scholarship program of Programa de Bolsas Itaú (PBI).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Nishimoto, B.E., Costa, A.H.R. (2021). Slot Sharing Mechanism in Multi-domain Dialogue Systems. In: Britto, A., Valdivia Delgado, K. (eds) Intelligent Systems. BRACIS 2021. Lecture Notes in Computer Science(), vol 13073. Springer, Cham. https://doi.org/10.1007/978-3-030-91702-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-91702-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91701-2
Online ISBN: 978-3-030-91702-9
eBook Packages: Computer ScienceComputer Science (R0)