Collaborative Knowledge Graph Fusion by Exploiting the Open Corpus

TL;DR

This paper introduces a collaborative framework for enriching knowledge graphs from open corpora by jointly performing join event extraction and graph fusion, improving the quality and accuracy of the enriched KG.

Contribution

It proposes a novel collaborative framework that enables mutual assistance between event extraction and graph fusion tasks, enhancing both processes through an iterative, aligned approach.

Findings

Improved accuracy in knowledge graph enrichment.

Enhanced performance of event extraction and graph fusion tasks.

Effective alignment of extracted triples with existing knowledge graphs.

Abstract

To alleviate the challenges of building Knowledge Graphs (KG) from scratch, a more general task is to enrich a KG using triples from an open corpus, where the obtained triples contain noisy entities and relations. It is challenging to enrich a KG with newly harvested triples while maintaining the quality of the knowledge representation. This paper proposes a system to refine a KG using information harvested from an additional corpus. To this end, we formulate our task as two coupled sub-tasks, namely join event extraction (JEE) and knowledge graph fusion (KGF). We then propose a Collaborative Knowledge Graph Fusion Framework to allow our sub-tasks to mutually assist one another in an alternating manner. More concretely, the explorer carries out the JEE supervised by both the ground-truth annotation and an existing KG provided by the supervisor. The supervisor then evaluates the triples extracted by the explorer and enriches the KG with those that are highly ranked. To implement this evaluation, we further propose a Translated Relation Alignment Scoring Mechanism to align and translate the extracted triples to the prior KG. Experiments verify that this collaboration can both improve the performance of the JEE and the KGF.