Analyzing the Influence of Knowledge Graph Information on Relation Extraction

TL;DR

This paper investigates how incorporating knowledge graph information improves relation extraction models, showing significant performance gains especially in imbalanced data scenarios across multiple datasets.

Contribution

It introduces a method combining relation extraction with graph-aware Neural Bellman-Ford networks, demonstrating consistent improvements in supervised and zero-shot settings.

Findings

Knowledge graph info enhances relation extraction performance.

Improvements are notable in imbalanced data scenarios.

Graph-aware neural networks outperform traditional methods.

Abstract

We examine the impact of incorporating knowledge graph information on the performance of relation extraction models across a range of datasets. Our hypothesis is that the positions of entities within a knowledge graph provide important insights for relation extraction tasks. We conduct experiments on multiple datasets, each varying in the number of relations, training examples, and underlying knowledge graphs. Our results demonstrate that integrating knowledge graph information significantly enhances performance, especially when dealing with an imbalance in the number of training examples for each relation. We evaluate the contribution of knowledge graph-based features by combining established relation extraction methods with graph-aware Neural Bellman-Ford networks. These features are tested in both supervised and zero-shot settings, demonstrating consistent performance improvements across various datasets.