A Neural Attention Model for Disfluency Detection

Shaolei Wang, Wanxiang Che, Ting Liu


Abstract
In this paper, we study the problem of disfluency detection using the encoder-decoder framework. We treat disfluency detection as a sequence-to-sequence problem and propose a neural attention-based model which can efficiently model the long-range dependencies between words and make the resulting sentence more likely to be grammatically correct. Our model firstly encode the source sentence with a bidirectional Long Short-Term Memory (BI-LSTM) and then use the neural attention as a pointer to select an ordered sub sequence of the input as the output. Experiments show that our model achieves the state-of-the-art f-score of 86.7% on the commonly used English Switchboard test set. We also evaluate the performance of our model on the in-house annotated Chinese data and achieve a significantly higher f-score compared to the baseline of CRF-based approach.
Anthology ID:
C16-1027
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
278–287
Language:
URL:
https://aclanthology.org/C16-1027
DOI:
Bibkey:
Cite (ACL):
Shaolei Wang, Wanxiang Che, and Ting Liu. 2016. A Neural Attention Model for Disfluency Detection. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 278–287, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
A Neural Attention Model for Disfluency Detection (Wang et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/C16-1027.pdf