Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling

Bo-Hsiang Tseng, Marek Rei, Paweł Budzianowski, Richard Turner, Bill Byrne, Anna Korhonen


Abstract
Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels. However, collecting these annotations is expensive and time-consuming, holding back development in the area of dialogue modelling. In this paper, we investigate semi-supervised learning methods that are able to reduce the amount of required intermediate labelling. We find that by leveraging un-annotated data instead, the amount of turn-level annotations of dialogue state can be significantly reduced when building a neural dialogue system. Our analysis on the MultiWOZ corpus, covering a range of domains and topics, finds that annotations can be reduced by up to 30% while maintaining equivalent system performance. We also describe and evaluate the first end-to-end dialogue model created for the MultiWOZ corpus.
Anthology ID:
D19-1125
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:
1273–1278
Language:
URL:
https://aclanthology.org/D19-1125
DOI:
10.18653/v1/D19-1125
Bibkey:
Cite (ACL):
Bo-Hsiang Tseng, Marek Rei, Paweł Budzianowski, Richard Turner, Bill Byrne, and Anna Korhonen. 2019. Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling. 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 1273–1278, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling (Tseng et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1125.pdf