← Search

Hiroto Kurita

2 accepted papers

2023

Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words

EMNLP 2023short findings

The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss. A natural question arises: what characteristics do models acquire during contrastive learning? This paper theoretically and experimentally shows that contrastive-base…

Cited by 0SourcecodeScholar