CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue

Libo Qin, Qiguang Chen, Tianbao Xie, Qian Liu, Shijue Huang, Wanxiang Che, Zhou Yu


Abstract
Consistency identification in task-oriented dialog (CI-ToD) usually consists of three subtasks, aiming to identify inconsistency between current system response and current user response, dialog history and the corresponding knowledge base. This work aims to solve CI-ToD task by introducing an explicit interaction paradigm, Cycle Guided Interactive learning Model (CGIM), which achieves to make information exchange explicitly from all the three tasks. Specifically, CGIM relies on two core insights, referred to as guided multi-head attention module and cycle interactive mechanism, that collaborate from each other. On the one hand, each two tasks are linked with the guided multi-head attention module, aiming to explicitly model the interaction across two related tasks. On the other hand, we further introduce cycle interactive mechanism that focuses on facilitating model to exchange information among the three correlated sub-tasks via a cycle interaction manner. Experimental results on CI-ToD benchmark show that our model achieves the state-of-the-art performance, pushing the overall score to 56.3% (5.0% point absolute improvement). In addition, we find that CGIM is robust to the initial task flow order.
Anthology ID:
2022.coling-1.37
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
461–470
Language:
URL:
https://aclanthology.org/2022.coling-1.37
DOI:
Bibkey:
Cite (ACL):
Libo Qin, Qiguang Chen, Tianbao Xie, Qian Liu, Shijue Huang, Wanxiang Che, and Zhou Yu. 2022. CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue. In Proceedings of the 29th International Conference on Computational Linguistics, pages 461–470, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue (Qin et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.37.pdf
Code
 lightchen233/cgim