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

[2305.14299] Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2305.14299 (cs) [Submitted on 23 May 2023 ( v1 ), last revised 12 Apr 2026 (this version, v3)] Title: Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings Authors: Minsik Oh , Jiwei Li , Guoyin Wang View a PDF of the paper titled Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings, by Minsik Oh and 2 other authors View PDF HTML (experimental) 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, \eg, 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 this https URL Comments: Accepted to ACL 2026 Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2305.14299 [cs.CL] (or arXiv:2305.14299v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2305.14299 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Minsik Oh [ view email ] [v1] Tue, 23 May 2023 17:40:41 UTC (7,161 KB) [v2] Sun, 30 Nov 2025 02:44:46 UTC (2,137 KB) [v3] Sun, 12 Apr 2026 00:03:25 UTC (2,139 KB) Full-text links: Access Paper: View a PDF of the paper titled Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings, by Minsik Oh and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2023-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue#620703
• FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue#619024
• Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning#464537
• Towards Debiasing Sentence Representations#335869
• PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue#1064531