SimCSE

2000년 도입 · 논문 52편에서 사용

SimCSE is a contrastive learning framework for generating sentence embeddings. It utilizes an unsupervised approach, which takes an input sentence and predicts itself in contrastive objective, with only standard dropout used as noise. The authors find that dropout acts as minimal “data augmentation” of hidden representations, while removing it leads to a representation collapse. Afterwards a supervised approach is used, which incorporates annotated pairs from natural language inference datasets into the contrastive framework, by using “entailment” pairs as positives and “contradiction

출처: SimCSE: Simple Contrastive Learning of Sentence Embeddings

소개 논문: SimCSE: Simple Contrastive Learning of Sentence Embeddings