A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond

TL;DR

This survey reviews recent advances in sentence representation learning, emphasizing deep learning methods from the BERT era to ChatGPT, and discusses challenges and future directions in NLP applications.

Contribution

It provides the first comprehensive literature review on sentence representations, systematically organizing methods and highlighting key contributions and challenges.

Findings

Significant progress in deep learning-based sentence representations

Identification of key challenges in representation quality and efficiency

Future research directions proposed for improved models

Abstract

Sentence representations are a critical component in NLP applications such as retrieval, question answering, and text classification. They capture the meaning of a sentence, enabling machines to understand and reason over human language. In recent years, significant progress has been made in developing methods for learning sentence representations, including unsupervised, supervised, and transfer learning approaches. However there is no literature review on sentence representations till now. In this paper, we provide an overview of the different methods for sentence representation learning, focusing mostly on deep learning models. We provide a systematic organization of the literature, highlighting the key contributions and challenges in this area. Overall, our review highlights the importance of this area in natural language processing, the progress made in sentence representation learning, and the challenges that remain. We conclude with directions for future research, suggesting potential avenues for improving the quality and efficiency of sentence representations.