Unsupervised Dialogue Spectrum Generation for Log Dialogue Ranking

Xinnuo Xu, Yizhe Zhang, Lars Liden, Sungjin Lee


Abstract
Although the data-driven approaches of some recent bot building platforms make it possible for a wide range of users to easily create dialogue systems, those platforms don’t offer tools for quickly identifying which log dialogues contain problems. This is important since corrections to log dialogues provide a means to improve performance after deployment. A log dialogue ranker, which ranks problematic dialogues higher, is an essential tool due to the sheer volume of log dialogues that could be generated. However, training a ranker typically requires labelling a substantial amount of data, which is not feasible for most users. In this paper, we present a novel unsupervised approach for dialogue ranking using GANs and release a corpus of labelled dialogues for evaluation and comparison with supervised methods. The evaluation result shows that our method compares favorably to supervised methods without any labelled data.
Anthology ID:
W19-5919
Volume:
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
Month:
September
Year:
2019
Address:
Stockholm, Sweden
Editors:
Satoshi Nakamura, Milica Gasic, Ingrid Zukerman, Gabriel Skantze, Mikio Nakano, Alexandros Papangelis, Stefan Ultes, Koichiro Yoshino
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
143–154
Language:
URL:
https://aclanthology.org/W19-5919
DOI:
10.18653/v1/W19-5919
Bibkey:
Cite (ACL):
Xinnuo Xu, Yizhe Zhang, Lars Liden, and Sungjin Lee. 2019. Unsupervised Dialogue Spectrum Generation for Log Dialogue Ranking. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 143–154, Stockholm, Sweden. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Dialogue Spectrum Generation for Log Dialogue Ranking (Xu et al., SIGDIAL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5919.pdf