Modeling Multi-Action Policy for Task-Oriented Dialogues

Lei Shu, Hu Xu, Bing Liu, Piero Molino


Abstract
Dialogue management (DM) plays a key role in the quality of the interaction with the user in a task-oriented dialogue system. In most existing approaches, the agent predicts only one DM policy action per turn. This significantly limits the expressive power of the conversational agent and introduces unwanted turns of interactions that may challenge users’ patience. Longer conversations also lead to more errors and the system needs to be more robust to handle them. In this paper, we compare the performance of several models on the task of predicting multiple acts for each turn. A novel policy model is proposed based on a recurrent cell called gated Continue-Act-Slots (gCAS) that overcomes the limitations of the existing models. Experimental results show that gCAS outperforms other approaches. The datasets and code are available at https://leishu02.github.io/.
Anthology ID:
D19-1130
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1304–1310
Language:
URL:
https://aclanthology.org/D19-1130
DOI:
10.18653/v1/D19-1130
Bibkey:
Cite (ACL):
Lei Shu, Hu Xu, Bing Liu, and Piero Molino. 2019. Modeling Multi-Action Policy for Task-Oriented Dialogues. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1304–1310, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Modeling Multi-Action Policy for Task-Oriented Dialogues (Shu et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1130.pdf