Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings

Minsik Oh, Jiwei Li, Guoyin Wang


Abstract
Learning high quality sentence embeddings from dialogues has drawn increasing attentions as it is essential to solve a variety of dialogue-oriented tasks with low annotation cost. Annotating and gathering utterance relationships in conversations are difficult, while token-level annotations, , entities, slots and templates, are much easier to obtain. Other sentence embedding methods are usually sentence-level self-supervised frameworks and cannot utilize token-level extra knowledge. We introduce Template-aware Dialogue Sentence Embedding (TaDSE), a novel augmentation method that utilizes template information to learn utterance embeddings via self-supervised contrastive learning framework. We further enhance the effect with a synthetically augmented dataset that diversifies utterance-template association, in which slot-filling is a preliminary step. We evaluate TaDSE performance on five downstream benchmark dialogue datasets. The experiment results show that TaDSE achieves significant improvements over previous SOTA methods for dialogue. We further introduce a novel analytic instrument of semantic compression test, for which we discover a correlation with uniformity and alignment. Our code is available at https://github.com/minsik-ai/Template-Contrastive-Embedding
Anthology ID:
2026.acl-long.1015
Volume:
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22181–22198
Language:
URL:
https://preview.aclanthology.org/ingest-acl/2026.acl-long.1015/
DOI:
Bibkey:
Cite (ACL):
Minsik Oh, Jiwei Li, and Guoyin Wang. 2026. Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 22181–22198, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings (Oh et al., ACL 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl/2026.acl-long.1015.pdf
Checklist:
 2026.acl-long.1015.checklist.pdf