SimCSE: Simple Contrastive Learning of Sentence Embeddings

Tianyu Gao, Xingcheng Yao, Danqi Chen


Abstract
This paper presents SimCSE, a simple contrastive learning framework that greatly advances the state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective, with only standard dropout used as noise. This simple method works surprisingly well, performing on par with previous supervised counterparts. We find that dropout acts as minimal data augmentation and removing it leads to a representation collapse. Then, we propose a supervised approach, which incorporates annotated pairs from natural language inference datasets into our contrastive learning framework, by using “entailment” pairs as positives and “contradiction” pairs as hard negatives. We evaluate SimCSE on standard semantic textual similarity (STS) tasks, and our unsupervised and supervised models using BERT base achieve an average of 76.3% and 81.6% Spearman’s correlation respectively, a 4.2% and 2.2% improvement compared to previous best results. We also show—both theoretically and empirically—that contrastive learning objective regularizes pre-trained embeddings’ anisotropic space to be more uniform, and it better aligns positive pairs when supervised signals are available.
Anthology ID:
2021.emnlp-main.552
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6894–6910
Language:
URL:
https://aclanthology.org/2021.emnlp-main.552
DOI:
10.18653/v1/2021.emnlp-main.552
Bibkey:
Cite (ACL):
Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6894–6910, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
SimCSE: Simple Contrastive Learning of Sentence Embeddings (Gao et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.552.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.552.mp4
Code
 princeton-nlp/SimCSE +  additional community code
Data
ANLIFlickr30kMultiNLISICKSNLISTS BenchmarkSentEval