DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo, Yang Zhang, Shiyu Chang, Marin Soljacic, Shang-Wen Li, Scott Yih
Abstract
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sentence, where the edited sentence is obtained by stochastically masking out the original sentence and then sampling from a masked language model. We show that DiffSCE is an instance of equivariant contrastive learning, which generalizes contrastive learning and learns representations that are insensitive to certain types of augmentations and sensitive to other “harmful” types of augmentations. Our experiments show that DiffCSE achieves state-of-the-art results among unsupervised sentence representation learning methods, outperforming unsupervised SimCSE by 2.3 absolute points on semantic textual similarity tasks.
BibTeX
@inproceedings{chuang-etal-2022-diffcse,
title = "{D}iff{CSE}: Difference-based Contrastive Learning for Sentence Embeddings",
author = "Chuang, Yung-Sung and
Dangovski, Rumen and
Luo, Hongyin and
Zhang, Yang and
Chang, Shiyu and
Soljacic, Marin and
Li, Shang-Wen and
Yih, Scott and
Kim, Yoon and
Glass, James",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.311/",
doi = "10.18653/v1/2022.naacl-main.311",
pages = "4207--4218"
}