An overview of the research landscape combining structured and unstructured knowledge in NLP
This post is based on our AACL-IJCNLP 2022 paper . As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP) and have experienced a rapid increase in popularity in recent years, a trend that appears to be accelerating 🚀. 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. 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.
What is Natural Language Processing?
Natural language processing (NLP) is a subfield of , and data .
Why do we use Knowledge Graphs in NLP?
The underlying paradigm is that the combination of structured and unstructured knowledge can benefit all kinds of NLP tasks. For instance, structured knowledge from KGs can be injected into that of the contextual knowledge found in language models, which improves the performance in downstream tasks () and GPT (
SOCIAL SHARE CARD GENERATOR