Text Transformations in Contrastive Self-Supervised Learning: A Review

TL;DR

This review paper discusses the challenges and methods of applying contrastive self-supervised learning to NLP, focusing on text transformations, evaluation, and future research directions.

Contribution

It formalizes the contrastive learning framework for NLP, reviews current state-of-the-art methods, and highlights key challenges and future directions.

Findings

Contrastive learning in NLP faces unique challenges due to semantic preservation during data augmentation.

Current methods vary in effectiveness and evaluation strategies for text representations.

Identifies open challenges and potential research directions in contrastive NLP.

Abstract

Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language Processing (NLP), the augmentation methods used in creating similar pairs with regard to contrastive learning (CL) assumptions are challenging. This is because, even simply modifying a word in the input might change the semantic meaning of the sentence, and hence, would violate the distributional hypothesis. In this review paper, we formalize the contrastive learning framework, emphasize the considerations that need to be addressed in the data transformation step, and review the state-of-the-art methods and evaluations for contrastive representation learning in NLP. Finally, we describe some challenges and potential directions for learning better text representations using contrastive methods.