Meta Learning for Natural Language Processing: A Survey
It provides a comprehensive resource for NLP researchers to access relevant meta-learning works, aiming to attract more attention and drive future innovation in the field.
This survey paper addresses the lack of a systematic review of meta-learning approaches in natural language processing (NLP), summarizing task construction settings and applications to improve data efficiency and generalizability across domains.
Deep learning has been the mainstream technique in natural language processing (NLP) area. However, the techniques require many labeled data and are less generalizable across domains. Meta-learning is an arising field in machine learning studying approaches to learn better learning algorithms. Approaches aim at improving algorithms in various aspects, including data efficiency and generalizability. Efficacy of approaches has been shown in many NLP tasks, but there is no systematic survey of these approaches in NLP, which hinders more researchers from joining the field. Our goal with this survey paper is to offer researchers pointers to relevant meta-learning works in NLP and attract more attention from the NLP community to drive future innovation. This paper first introduces the general concepts of meta-learning and the common approaches. Then we summarize task construction settings and application of meta-learning for various NLP problems and review the development of meta-learning in NLP community.