Learning Relation Ties with a Force-Directed Graph in Distant Supervised Relation Extraction

TL;DR

This paper introduces a novel force-directed graph model for distant supervised relation extraction that captures global relation ties using physics-inspired forces, significantly improving extraction accuracy.

Contribution

It proposes a global topology-aware relation extraction model using Coulomb's Law inspired forces, outperforming local dependency-based methods.

Findings

Model captures global relation ties effectively.

Significant performance improvement over baselines.

Force-directed graph enhances existing systems.

Abstract

Relation ties, defined as the correlation and mutual exclusion between different relations, are critical for distant supervised relation extraction. Existing approaches model this property by greedily learning local dependencies. However, they are essentially limited by failing to capture the global topology structure of relation ties. As a result, they may easily fall into a locally optimal solution. To solve this problem, in this paper, we propose a novel force-directed graph based relation extraction model to comprehensively learn relation ties. Specifically, we first build a graph according to the global co-occurrence of relations. Then, we borrow the idea of Coulomb's Law from physics and introduce the concept of attractive force and repulsive force to this graph to learn correlation and mutual exclusion between relations. Finally, the obtained relation representations are applied as an inter-dependent relation classifier. Experimental results on a large scale benchmark dataset demonstrate that our model is capable of modeling global relation ties and significantly outperforms other baselines. Furthermore, the proposed force-directed graph can be used as a module to augment existing relation extraction systems and improve their performance.