DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
This addresses the limitation of requiring labeled data for high-performing sentence embeddings, benefiting NLP applications in languages and domains with scarce labeled data.
The paper tackles the problem of learning sentence embeddings without labeled data by proposing DeCLUTR, a self-supervised method using deep contrastive learning, which closes the performance gap between unsupervised and supervised pretraining for universal sentence encoders.
Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such as clustering and retrieval. Unlike word embeddings, the highest performing solutions for learning sentence embeddings require labelled data, limiting their usefulness to languages and domains where labelled data is abundant. In this paper, we present DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations. Inspired by recent advances in deep metric learning (DML), we carefully design a self-supervised objective for learning universal sentence embeddings that does not require labelled training data. When used to extend the pretraining of transformer-based language models, our approach closes the performance gap between unsupervised and supervised pretraining for universal sentence encoders. Importantly, our experiments suggest that the quality of the learned embeddings scale with both the number of trainable parameters and the amount of unlabelled training data. Our code and pretrained models are publicly available and can be easily adapted to new domains or used to embed unseen text.