Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey

TL;DR

This survey reviews the development of Knowledge Enhanced Pretrained Language Models, highlighting their methods, applications, challenges, and future directions in improving NLP performance by integrating external knowledge.

Contribution

It provides a comprehensive taxonomy and analysis of KE-PLMs, covering recent approaches, applications, and future research challenges in the field.

Findings

KE-PLMs outperform vanilla PLMs in various NLP tasks.

Multiple approaches exist for integrating knowledge into PLMs.

Future research faces challenges like knowledge consistency and scalability.

Abstract

Pretrained Language Models (PLM) have established a new paradigm through learning informative contextualized representations on large-scale text corpus. This new paradigm has revolutionized the entire field of natural language processing, and set the new state-of-the-art performance for a wide variety of NLP tasks. However, though PLMs could store certain knowledge/facts from training corpus, their knowledge awareness is still far from satisfactory. To address this issue, integrating knowledge into PLMs have recently become a very active research area and a variety of approaches have been developed. In this paper, we provide a comprehensive survey of the literature on this emerging and fast-growing field - Knowledge Enhanced Pretrained Language Models (KE-PLMs). We introduce three taxonomies to categorize existing work. Besides, we also survey the various NLU and NLG applications on which KE-PLM has demonstrated superior performance over vanilla PLMs. Finally, we discuss challenges that face KE-PLMs and also promising directions for future research.