A Decade of Knowledge Graphs in Natural Language Processing: A Survey

TL;DR

This survey reviews a decade of research on knowledge graphs in NLP, categorizing topics, analyzing research trends, and identifying future directions based on 507 papers.

Contribution

It provides the first comprehensive taxonomy and analysis of research streams in knowledge graphs within NLP, covering 507 papers.

Findings

Knowledge graphs are increasingly integrated into NLP tasks.

Research in KGs for NLP has matured with diverse applications.

Future work should focus on standardization and scalability.

Abstract

In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.