Improving Dialogue State Tracking by Joint Slot Modeling

Ting-Rui Chiang, Yi-Ting Yeh


Abstract
Dialogue state tracking models play an important role in a task-oriented dialogue system. However, most of them model the slot types conditionally independently given the input. We discover that it may cause the model to be confused by slot types that share the same data type. To mitigate this issue, we propose TripPy-MRF and TripPy-LSTM that models the slots jointly. Our results show that they are able to alleviate the confusion mentioned above, and they push the state-of-the-art on dataset MultiWoz 2.1 from 58.7 to 61.3.
Anthology ID:
2021.nlp4convai-1.15
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
Month:
November
Year:
2021
Address:
Online
Venues:
EMNLP | NLP4ConvAI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
155–162
Language:
URL:
https://aclanthology.org/2021.nlp4convai-1.15
DOI:
10.18653/v1/2021.nlp4convai-1.15
Bibkey:
Cite (ACL):
Ting-Rui Chiang and Yi-Ting Yeh. 2021. Improving Dialogue State Tracking by Joint Slot Modeling. In Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pages 155–162, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Dialogue State Tracking by Joint Slot Modeling (Chiang & Yeh, NLP4ConvAI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.nlp4convai-1.15.pdf