ICDM 2019 Knowledge Graph Contest: Team UWA

TL;DR

This paper describes a pipeline-based system for extracting triples from domain-specific texts to construct knowledge graphs, including visualization features for analysis.

Contribution

It introduces a simple, effective triple extraction pipeline with visualization capabilities for knowledge graph construction from text.

Findings

Effective triple extraction from domain-specific text

Visualization tools for triple analysis

Successful application in knowledge graph construction

Abstract

We present an overview of our triple extraction system for the ICDM 2019 Knowledge Graph Contest. Our system uses a pipeline-based approach to extract a set of triples from a given document. It offers a simple and effective solution to the challenge of knowledge graph construction from domain-specific text. It also provides the facility to visualise useful information about each triple such as the degree, betweenness, structured relation type(s), and named entity types.