Text Transformations in Contrastive Self-Supervised Learning: A Review

By Amrita Bhattacharjee, Mansooreh Karami, Huan Liu. 2022

25 citations recorded by the source corpus.

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.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

1. Amir Globerson
2. Omer Levy
3. Jonathan Berant
4. Ori Ram
5. Yoav Goldberg
6. Ido Dagan
7. Sunipa Dev
8. Ivan Vulic

Citations in the corpus

• Learning to Retrieve Passages without Supervision (2021, background): “supervision only (Bhattacharjee et al., 2022), which achieves retrieval accuracy that significantly improves over unsupervised methods (both contrastive and end-to-end), and is much cheaper to train compared to end-to-end models.”