A Simple Angle-based Approach for Contrastive Learning of Unsupervised Sentence Representation

Yoo Hyun Jeong, Myeongsoo Han, Dong-Kyu Chae


Abstract
Contrastive learning has been successfully adopted in VRL (visual representation learning) by constructing effective contrastive pairs. A promising baseline SimCSE has made notable breakthroughs in unsupervised SRL (sentence representation learning) following the success of contrastive learning. However, considering the difference between VRL and SRL, there is still room for designing a novel contrastive framework specially targeted for SRL. We pro- pose a novel angle-based similarity function for contrastive objective. By examining the gra- dient of our contrastive objective, we show that an angle-based similarity function incites better training dynamics on SRL than the off-the-shelf cosine similarity: (1) effectively pulling a posi- tive instance toward an anchor instance in the early stage of training and (2) not excessively repelling a false negative instance during the middle of training. Our experimental results on widely-utilized benchmarks demonstrate the ef- fectiveness and extensibility of our novel angle- based approach. Subsequent analyses establish its improved sentence representation power.
Anthology ID:
2024.findings-emnlp.318
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5553–5572
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.318
DOI:
Bibkey:
Cite (ACL):
Yoo Hyun Jeong, Myeongsoo Han, and Dong-Kyu Chae. 2024. A Simple Angle-based Approach for Contrastive Learning of Unsupervised Sentence Representation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5553–5572, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
A Simple Angle-based Approach for Contrastive Learning of Unsupervised Sentence Representation (Jeong et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.318.pdf