Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding

Jonggu Kim, Jong-Hyeok Lee


Abstract
To capture salient contextual information for spoken language understanding (SLU) of a dialogue, we propose time-aware models that automatically learn the latent time-decay function of the history without a manual time-decay function. We also propose a method to identify and label the current speaker to improve the SLU accuracy. In experiments on the benchmark dataset used in Dialog State Tracking Challenge 4, the proposed models achieved significantly higher F1 scores than the state-of-the-art contextual models. Finally, we analyze the effectiveness of the introduced models in detail. The analysis demonstrates that the proposed methods were effective to improve SLU accuracy individually.
Anthology ID:
N19-1372
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3718–3726
Language:
URL:
https://aclanthology.org/N19-1372
DOI:
10.18653/v1/N19-1372
Bibkey:
Cite (ACL):
Jonggu Kim and Jong-Hyeok Lee. 2019. Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3718–3726, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding (Kim & Lee, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1372.pdf
Code
 jgkimi/Decay-Function-Free-Time-Aware