Self-Supervised Dialogue Learning

Jiawei Wu, Xin Wang, William Yang Wang


Abstract
The sequential order of utterances is often meaningful in coherent dialogues, and the order changes of utterances could lead to low-quality and incoherent conversations. We consider the order information as a crucial supervised signal for dialogue learning, which, however, has been neglected by many previous dialogue systems. Therefore, in this paper, we introduce a self-supervised learning task, inconsistent order detection, to explicitly capture the flow of conversation in dialogues. Given a sampled utterance pair triple, the task is to predict whether it is ordered or misordered. Then we propose a sampling-based self-supervised network SSN to perform the prediction with sampled triple references from previous dialogue history. Furthermore, we design a joint learning framework where SSN can guide the dialogue systems towards more coherent and relevant dialogue learning through adversarial training. We demonstrate that the proposed methods can be applied to both open-domain and task-oriented dialogue scenarios, and achieve the new state-of-the-art performance on the OpenSubtitiles and Movie-Ticket Booking datasets.
Anthology ID:
P19-1375
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3857–3867
Language:
URL:
https://aclanthology.org/P19-1375
DOI:
10.18653/v1/P19-1375
Bibkey:
Cite (ACL):
Jiawei Wu, Xin Wang, and William Yang Wang. 2019. Self-Supervised Dialogue Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3857–3867, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Self-Supervised Dialogue Learning (Wu et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1375.pdf