Abstract
Dialog act segmentation and recognition are basic natural language understanding tasks in spoken dialog systems. This paper investigates a unified architecture for these two tasks, which aims to improve the model’s performance on both of the tasks. Compared with past joint models, the proposed architecture can (1) incorporate contextual information in dialog act recognition, and (2) integrate models for tasks of different levels as a whole, i.e. dialog act segmentation on the word level and dialog act recognition on the segment level. Experimental results show that the joint training system outperforms the simple cascading system and the joint coding system on both dialog act segmentation and recognition tasks.- Anthology ID:
- I17-1071
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 704–712
- Language:
- URL:
- https://aclanthology.org/I17-1071
- DOI:
- Cite (ACL):
- Tianyu Zhao and Tatsuya Kawahara. 2017. Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 704–712, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks (Zhao & Kawahara, IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/I17-1071.pdf