A Continual Relation Extraction Approach for Knowledge Graph Completeness

TL;DR

This paper introduces a continual relation extraction method designed to identify inter-entity relations in real-time data streams, specifically applied to corona news from German and Austrian newspapers, to enhance knowledge graph completeness.

Contribution

It proposes a novel continual relation extraction approach tailored for real-world, domain-specific data streams, improving knowledge graph construction from unstructured news data.

Findings

Effective relation extraction from corona news streams

Improved knowledge graph completeness in the domain

Demonstrated applicability to real-world data

Abstract

Representing unstructured data in a structured form is most significant for information system management to analyze and interpret it. To do this, the unstructured data might be converted into Knowledge Graphs, by leveraging an information extraction pipeline whose main tasks are named entity recognition and relation extraction. This thesis aims to develop a novel continual relation extraction method to identify relations (interconnections) between entities in a data stream coming from the real world. Domain-specific data of this thesis is corona news from German and Austrian newspapers.