Smoothed Contrastive Learning for Unsupervised Sentence Embedding
Contrastive learning has been gradually applied to learn high-quality unsupervised sentence embedding. Among the previous un-supervised methods, the latest state-of-the-art method, as far as we know, is unsupervised SimCSE (unsup-SimCSE). Unsup-SimCSE uses the InfoNCE1loss function in the training stage by pulling semantically similar sentences together and pushing apart dis-similar ones.Theoretically, we expect to use larger batches in unsup-SimCSE to get more adequate comparisons among samples and avoid overfitting. However, increasing the batch size does not always lead to improvements, but instead even lead to performance degradation when the batch size exceeds a threshold. Through statistical observation, we find that this is probably due to the introduction of low-confidence negative pairs after in-creasing the batch size. To alleviate this problem, we introduce a simple smoothing strategy upon the InfoNCE loss function, termedGaussian Smoothing InfoNCE (GS-InfoNCE).Specifically, we add random Gaussian noise vectors as negative samples, which act asa smoothing of the negative sample space.Though being simple, the proposed smooth-ing strategy brings substantial improvements to unsup-SimCSE. We evaluate GS-InfoNCEon the standard semantic text similarity (STS)task. GS-InfoNCE outperforms the state-of-the-art unsup-SimCSE by an average Spear-man correlation of 1.38%, 0.72%, 1.17% and0.28% on the base of BERT-base, BERT-large,RoBERTa-base and RoBERTa-large, respectively.
Code (2)
Tasks
Contrastive LearningSentenceSentence EmbeddingSentence-EmbeddingSTStext similarityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Instance Smoothed Contrastive Learning for Unsupervised Sentence Embedding
Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous studies, each embedding used for contrastive…
Contrastive LearningSemantic SimilaritySemantic Textual SimilaritySentence+5PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings
Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success …
Contrastive LearningOpen-Ended Question AnsweringSentenceSentence Embeddings+1DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sen…
Contrastive LearningLanguage ModelingLanguage ModellingRepresentation Learning+3DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective
Several prior studies have suggested that word frequency biases can cause the Bert model to learn indistinguishable sentence embeddings. Contrastive learning schemes such as SimCSE and ConSERT have already been adopted s…
Contrastive LearningSemantic SimilaritySemantic Textual SimilaritySentence+4UNSEE: Unsupervised Non-contrastive Sentence Embeddings
We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation c…
SentenceSentence Embeddings