Speaker-change Aware CRF for Dialogue Act Classification

Guokan Shang, Antoine Tixier, Michalis Vazirgiannis, Jean-Pierre Lorré


Abstract
Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. CRF models the conditional probability of the target DA label sequence given the input utterance sequence. However, the task involves another important input sequence, that of speakers, which is ignored by previous work. To address this limitation, this paper proposes a simple modification of the CRF layer that takes speaker-change into account. Experiments on the SwDA corpus show that our modified CRF layer outperforms the original one, with very wide margins for some DA labels. Further, visualizations demonstrate that our CRF layer can learn meaningful, sophisticated transition patterns between DA label pairs conditioned on speaker-change in an end-to-end way. Code is publicly available.
Anthology ID:
2020.coling-main.40
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
450–464
Language:
URL:
https://aclanthology.org/2020.coling-main.40
DOI:
10.18653/v1/2020.coling-main.40
Bibkey:
Cite (ACL):
Guokan Shang, Antoine Tixier, Michalis Vazirgiannis, and Jean-Pierre Lorré. 2020. Speaker-change Aware CRF for Dialogue Act Classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 450–464, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Speaker-change Aware CRF for Dialogue Act Classification (Shang et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.40.pdf
Code
 guokan_shang/da-classification +  additional community code
Data
Switchboard Dialog Act Corpus