ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Semantic Textual Similarity | STS tasks (STS12, STS13, STS14, STS15, STS16, STS-B, SICK-R) various (test) | STS12 Score77.47 | 393 | |
| Semantic Textual Similarity | STS tasks (STS12, STS13, STS14, STS15, STS16, STS-B, SICK-R) | STS12 Score70.69 | 195 | |
| Semantic Textual Similarity | STS (Semantic Textual Similarity) 2012-2016 (test) | STS-12 Score74.07 | 57 |