Q-TOD: A Query-driven Task-oriented Dialogue System

Xin Tian, Yingzhan Lin, Mengfei Song, Siqi Bao, Fan Wang, Huang He, Shuqi Sun, Hua Wu


Abstract
Existing pipelined task-oriented dialogue systems usually have difficulties adapting to unseen domains, whereas end-to-end systems are plagued by large-scale knowledge bases in practice. In this paper, we introduce a novel query-driven task-oriented dialogue system, namely Q-TOD. The essential information from the dialogue context is extracted into a query, which is further employed to retrieve relevant knowledge records for response generation. Firstly, as the query is in the form of natural language and not confined to the schema of the knowledge base, the issue of domain adaption is alleviated remarkably in Q-TOD. Secondly, as the query enables the decoupling of knowledge retrieval from the generation, Q-TOD gets rid of the issue of knowledge base scalability. To evaluate the effectiveness of the proposed Q-TOD, we collect query annotations for three publicly available task-oriented dialogue datasets. Comprehensive experiments verify that Q-TOD outperforms strong baselines and establishes a new state-of-the-art performance on these datasets.
Anthology ID:
2022.emnlp-main.489
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7260–7271
Language:
URL:
https://aclanthology.org/2022.emnlp-main.489
DOI:
10.18653/v1/2022.emnlp-main.489
Bibkey:
Cite (ACL):
Xin Tian, Yingzhan Lin, Mengfei Song, Siqi Bao, Fan Wang, Huang He, Shuqi Sun, and Hua Wu. 2022. Q-TOD: A Query-driven Task-oriented Dialogue System. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7260–7271, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Q-TOD: A Query-driven Task-oriented Dialogue System (Tian et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.489.pdf