PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings

Qiyu Wu, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng, Daxin Jiang


Abstract
Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting a sentence with a semantically-close positive instance to construct contrastive pairs. Nonetheless, existing approaches usually depend on a mono-augmenting strategy, which causes learning shortcuts towards the augmenting biases and thus corrupts the quality of sentence embeddings. A straightforward solution is resorting to more diverse positives from a multi-augmenting strategy, while an open question remains about how to unsupervisedly learn from the diverse positives but with uneven augmenting qualities in the text field. As one answer, we propose a novel Peer-Contrastive Learning (PCL) with diverse augmentations. PCL constructs diverse contrastive positives and negatives at the group level for unsupervised sentence embeddings. PCL performs peer-positive contrast as well as peer-network cooperation, which offers an inherent anti-bias ability and an effective way to learn from diverse augmentations. Experiments on STS benchmarks verify the effectiveness of PCL against its competitors in unsupervised sentence embeddings.
Anthology ID:
2022.emnlp-main.826
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12052–12066
Language:
URL:
https://aclanthology.org/2022.emnlp-main.826
DOI:
Bibkey:
Cite (ACL):
Qiyu Wu, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng, and Daxin Jiang. 2022. PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 12052–12066, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings (Wu et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.826.pdf