Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing

Osman Ramadan, Paweł Budzianowski, Milica Gašić


Abstract
Robust dialogue belief tracking is a key component in maintaining good quality dialogue systems. The tasks that dialogue systems are trying to solve are becoming increasingly complex, requiring scalability to multi-domain, semantically rich dialogues. However, most current approaches have difficulty scaling up with domains because of the dependency of the model parameters on the dialogue ontology. In this paper, a novel approach is introduced that fully utilizes semantic similarity between dialogue utterances and the ontology terms, allowing the information to be shared across domains. The evaluation is performed on a recently collected multi-domain dialogues dataset, one order of magnitude larger than currently available corpora. Our model demonstrates great capability in handling multi-domain dialogues, simultaneously outperforming existing state-of-the-art models in single-domain dialogue tracking tasks.
Anthology ID:
P18-2069
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
432–437
Language:
URL:
https://aclanthology.org/P18-2069
DOI:
10.18653/v1/P18-2069
Bibkey:
Cite (ACL):
Osman Ramadan, Paweł Budzianowski, and Milica Gašić. 2018. Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 432–437, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing (Ramadan et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-2069.pdf
Presentation:
 P18-2069.Presentation.pdf
Video:
 https://aclanthology.org/P18-2069.mp4
Code
 additional community code
Data
MultiWOZ