RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network

Abstract

In this paper, we present a novel method named RECON, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG). RECON uses a graph neural network to learn representations of both the sentence as well as facts stored in a KG, improving the overall extraction quality. These facts, including entity attributes (label, alias, description, instance-of) and factual triples, have not been collectively used in the state of the art methods. We evaluate the effect of various forms of representing the KG context on the performance of RECON. The empirical evaluation on two standard relation extraction datasets shows that RECON significantly outperforms all state of the art methods on NYT Freebase and Wikidata datasets.

Authors 6

1. Anson Bastos

   Indian Institute of Technology Hyderabad

   Affiliation as printed

   Indian Institute of Technology, Hyderabad and Zerotha Research, India

   [Indian Institute of Technology, Hyderabad]

2. Abhishek Nadgeri Aachen Zerotha Research and

   RWTH Aachen University

   Affiliation as printed

   Zerotha Research and RWTH Aachen, Germany

3. Kuldeep Singh
   Affiliation as printed

   Zerotha Research and Cerence GmbH, Germany

4. Isaiah Onando Mulang

   University of Bonn · Fraunhofer Institute for Intelligent Analysis and Information Systems

   Affiliation as printed

   Zerotha Research and Fraunhofer IAIS, Germany

   University of Bonn > > > >

5. Saeedeh Shekarpour

   University of Dayton

   Affiliation as printed

   University of Dayton, USA

   University of Dayton

6. Johannes Hoffart

   Goldman Sachs (United States)

   Affiliation as printed

   Goldman Sachs, Germany

   Goldman Sachs