English

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Computation and Language 2021-05-26 v1 Artificial Intelligence

Abstract

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence representations are proved to be collapsed and thus produce a poor performance on the semantic textual similarity (STS) tasks. In this paper, we present ConSERT, a Contrastive Framework for Self-Supervised Sentence Representation Transfer, that adopts contrastive learning to fine-tune BERT in an unsupervised and effective way. By making use of unlabeled texts, ConSERT solves the collapse issue of BERT-derived sentence representations and make them more applicable for downstream tasks. Experiments on STS datasets demonstrate that ConSERT achieves an 8\% relative improvement over the previous state-of-the-art, even comparable to the supervised SBERT-NLI. And when further incorporating NLI supervision, we achieve new state-of-the-art performance on STS tasks. Moreover, ConSERT obtains comparable results with only 1000 samples available, showing its robustness in data scarcity scenarios.

Keywords

Cite

@article{arxiv.2105.11741,
  title  = {ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer},
  author = {Yuanmeng Yan and Rumei Li and Sirui Wang and Fuzheng Zhang and Wei Wu and Weiran Xu},
  journal= {arXiv preprint arXiv:2105.11741},
  year   = {2021}
}

Comments

Accepted by ACL2021, 10 pages, 7 figures, 4 tables

R2 v1 2026-06-24T02:26:12.345Z