Global-Locally Self-Attentive Encoder for Dialogue State Tracking

Victor Zhong, Caiming Xiong, Richard Socher

[How to correct problems with metadata yourself]


Abstract
Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to shares parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states. GLAD obtains 88.3% joint goal accuracy and 96.4% request accuracy on the WoZ state tracking task, outperforming prior work by 3.9% and 4.8%. On the DSTC2 task, our model obtains 74.7% joint goal accuracy and 97.3% request accuracy, outperforming prior work by 1.3% and 0.8%
Anthology ID:
P18-1135
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1458–1467
Language:
URL:
https://aclanthology.org/P18-1135
DOI:
10.18653/v1/P18-1135
Bibkey:
Cite (ACL):
Victor Zhong, Caiming Xiong, and Richard Socher. 2018. Global-Locally Self-Attentive Encoder for Dialogue State Tracking. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1458–1467, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Global-Locally Self-Attentive Encoder for Dialogue State Tracking (Zhong et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/P18-1135.pdf
Poster:
 P18-1135.Poster.pdf