Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation

Liliang Ren, Jianmo Ni, Julian McAuley


Abstract
Existing approaches to dialogue state tracking rely on pre-defined ontologies consisting of a set of all possible slot types and values. Though such approaches exhibit promising performance on single-domain benchmarks, they suffer from computational complexity that increases proportionally to the number of pre-defined slots that need tracking. This issue becomes more severe when it comes to multi-domain dialogues which include larger numbers of slots. In this paper, we investigate how to approach DST using a generation framework without the pre-defined ontology list. Given each turn of user utterance and system response, we directly generate a sequence of belief states by applying a hierarchical encoder-decoder structure. In this way, the computational complexity of our model will be a constant regardless of the number of pre-defined slots. Experiments on both the multi-domain and the single domain dialogue state tracking dataset show that our model not only scales easily with the increasing number of pre-defined domains and slots but also reaches the state-of-the-art performance.
Anthology ID:
D19-1196
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1876–1885
Language:
URL:
https://aclanthology.org/D19-1196
DOI:
10.18653/v1/D19-1196
Bibkey:
Cite (ACL):
Liliang Ren, Jianmo Ni, and Julian McAuley. 2019. Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1876–1885, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation (Ren et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1196.pdf
Code
 renll/ComerNet
Data
MultiWOZ