Continual Learning of Natural Language Processing Tasks: A Survey
It provides a comprehensive overview for researchers in NLP, but is incremental as it builds on existing surveys by adding new topics.
This survey tackles the problem of continual learning in natural language processing by reviewing recent progress, covering unique aspects like knowledge transfer and inter-task class separation that differ from other fields.
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.