Viet-Anh on Software Logo

What is: Mirror-BERT?

SourceFast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Mirror-BERT converts pretrained language models into effective universal text encoders without any supervision, in 20-30 seconds. It is an extremely simple, fast, and effective contrastive learning technique. It relies on fully identical or slightly modified string pairs as positive (i.e., synonymous) fine-tuning examples, and aims to maximise their similarity during identity fine-tuning.