Learning Dialogue Representations from Consecutive Utterances

Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew Arnold, Bing Xiang


Abstract
Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue tasks. DSE learns from dialogues by taking consecutive utterances of the same dialogue as positive pairs for contrastive learning. Despite its simplicity, DSE achieves significantly better representation capability than other dialogue representation and universal sentence representation models. We evaluate DSE on five downstream dialogue tasks that examine dialogue representation at different semantic granularities. Experiments in few-shot and zero-shot settings show that DSE outperforms baselines by a large margin, for example, it achieves 13% average performance improvement over the strongest unsupervised baseline in 1-shot intent classification on 6 datasets. We also provide analyses on the benefits and limitations of our model.
Anthology ID:
2022.naacl-main.55
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
754–768
Language:
URL:
https://aclanthology.org/2022.naacl-main.55
DOI:
10.18653/v1/2022.naacl-main.55
Bibkey:
Cite (ACL):
Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew Arnold, and Bing Xiang. 2022. Learning Dialogue Representations from Consecutive Utterances. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 754–768, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Learning Dialogue Representations from Consecutive Utterances (Zhou et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.55.pdf
Video:
 https://aclanthology.org/2022.naacl-main.55.mp4
Code
 amazon-research/dse
Data
AmazonQABANKING77-OOSCLINC-Single-Domain-OOSCLINC150DSTC7 Task 1HWU64SNIPS