Abstract
In a task-oriented dialogue system, the dialogue state tracker aims to generate a structured summary (domain-slot-value triples) over the whole dialogue utterance. However, existing approaches generally fail to make good use of pre-defined ontologies. In this paper, we propose a novel Memory Attention State Tracker that considers ontologies as prior knowledge and utilizes Memory Network to store such information. Our model is composed of an utterance encoder, an attention-based query generator, a slot gate classifier, and ontology Memory Networks for every domain-slot pair. To make a fair comparison with previous approaches, we also conduct experiments with RNN instead of pre-trained BERT as the encoder. Empirical results show that our model achieves a compatible joint accuracy on MultiWoz 2.0 dataset and MultiWoz 2.1 dataset.
Z. Xu and Z. Chen—Co-first authors and contribute equally to this work.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
For brevity, the subscript t of \(\mathbf {h}_t^k\) will be omitted in the following sections.
- 2.
For brevity, the subscript indicating the (domain, slot) pair is omitted in this section and next section.
- 3.
When the size of embedding vector and the size of BERT embedding are different, a linear transformation layer will be used.
References
Budzianowski, P., et al.: Multiwoz-a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 5016–5026 (2018)
Chen, H., Liu, X., Yin, D., Tang, J.: A survey on dialogue systems: recent advances and new frontiers. ACM Sigkdd Explor. Newslett. 19(2), 25–35 (2017)
Chen, L., Chen, Z., Tan, B., Long, S., Gašić, M., Yu, K.: Agentgraph: toward universal dialogue management with structured deep reinforcement learning. IEEE/ACM Trans. Audio Speech Lang. Process. 27(9), 1378–1391 (2019)
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: AAAI, pp. 7521–7528 (2020)
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In NAACL (2019)
Eric, M., et al.: Multiwoz 2.1: Multi-domain dialogue state corrections and state tracking baselines. arXiv preprint arXiv:1907.01669 (2019)
Goddeau, D., Meng, H., Polifroni, J., Seneff, S., Busayapongchai, S.: A form-based dialogue manager for spoken language applications. In: Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP 1996, vol. 2, pp. 701–704. IEEE (1996)
Goel, R., Paul, S., Hakkani-Tür, D.: Hyst: a hybrid approach for flexible and accurate dialogue state tracking. arXiv preprint arXiv:1907.00883 (2019)
Hashimoto, K., Xiong, C., Tsuruoka, Y., Socher, R.: A joint many-task model: Growing a neural network for multiple nlp tasks. arXiv preprint arXiv:1611.01587 (2016)
Heck, M., et al.: Trippy: a triple copy strategy for value independent neural dialog state tracking. arXiv preprint arXiv:2005.02877 (2020)
Kim, S., Yang, S., Kim, G., Lee, S.W.: Efficient dialogue state tracking by selectively overwriting memory. arXiv preprint arXiv:1911.03906 (2019)
Liu, B., Lane, I.: An end-to-end trainable neural network model with belief tracking for task-oriented dialog. In INTERSPEECH (2017)
Paul, S., Goel, R., Hakkani-Tür, D.: Towards universal dialogue act tagging for task-oriented dialogues. arXiv preprint arXiv:1907.03020 (2019)
Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1532–1543 (2014)
Perez, J., Liu, F.: Dialog state tracking, a machine reading approach using memory network. arXiv preprint arXiv:1606.04052 (2016)
Sukhbaatar, S., et al.: End-to-end memory networks. In: Advances in Neural Information Processing Systems, pp. 2440–2448 (2015)
Wen, T.H., et al.: A network-based end-to-end trainable task-oriented dialogue system. In: EACL (2016)
Wu, C.S., Madotto, A., Hosseini-Asl, E., Xiong, C., Socher, R., Fung, P.: Transferable multi-domain state generator for task-oriented dialogue systems. arXiv preprint arXiv:1905.08743 (2019)
Zhang, J.G., et al.: Find or classify? Dual strategy for slot-value predictions on multi-domain dialog state tracking. arXiv preprint arXiv:1910.03544 (2019)
Zhong, V., Xiong, C., Socher, R.: Global-locally self-attentive dialogue state tracker. arXiv preprint arXiv:1805.09655 (2018)
Acknowledgement
We thank the anonymous reviewers for their thoughtful comments. This work has been supported by the National Key Research and Development Program of China (Grant No. 2017YFB1002102) and Shanghai Jiao Tong University Scientific and Technological Innovation Funds (YG2020YQ01).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, Z., Chen, Z., Chen, L., Zhu, S., Yu, K. (2020). Memory Attention Neural Network for Multi-domain Dialogue State Tracking. In: Zhu, X., Zhang, M., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2020. Lecture Notes in Computer Science(), vol 12430. Springer, Cham. https://doi.org/10.1007/978-3-030-60450-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-60450-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60449-3
Online ISBN: 978-3-030-60450-9
eBook Packages: Computer ScienceComputer Science (R0)