Continual Learning of Natural Language Processing Tasks: A Survey

TL;DR

This survey reviews recent advances in continual learning for NLP, highlighting unique challenges, techniques, and future directions, emphasizing differences from vision and general machine learning CL.

Contribution

It provides a comprehensive taxonomy of CL techniques in NLP, discusses new aspects like inter-task class separation, and covers recent progress not included in prior surveys.

Findings

Identifies key CL settings and techniques in NLP.

Highlights importance of knowledge transfer and inter-task class separation.

Discusses future research directions in NLP continual learning.

Abstract

Continual learning (CL) is a learning paradigm that emulates the human capability of learning and accumulating knowledge continually without forgetting the previously learned knowledge and also transferring the learned knowledge to help learn new tasks better. This survey presents a comprehensive review and analysis of the recent progress of CL in NLP, which has significant differences from CL in computer vision and machine learning. It covers (1) all CL settings with a taxonomy of existing techniques; (2) catastrophic forgetting (CF) prevention, (3) knowledge transfer (KT), which is particularly important for NLP tasks; and (4) some theory and the hidden challenge of inter-task class separation (ICS). (1), (3) and (4) have not been included in the existing survey. Finally, a list of future directions is discussed.