Pretraining Methods for Dialog Context Representation Learning

Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao, Maxine Eskenazi


Abstract
This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed, and a total of four methods are examined. Each pretraining objective is fine-tuned and evaluated on a set of downstream dialog tasks using the MultiWoz dataset and strong performance improvement is observed. Further evaluation shows that our pretraining objectives result in not only better performance, but also better convergence, models that are less data hungry and have better domain generalizability.
Anthology ID:
P19-1373
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:
3836–3845
Language:
URL:
https://aclanthology.org/P19-1373
DOI:
10.18653/v1/P19-1373
Bibkey:
Cite (ACL):
Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao, and Maxine Eskenazi. 2019. Pretraining Methods for Dialog Context Representation Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3836–3845, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Pretraining Methods for Dialog Context Representation Learning (Mehri et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1373.pdf
Supplementary:
 P19-1373.Supplementary.pdf