A Dependency-Based Neural Network for Relation Classification

TL;DR

This paper introduces a novel neural network model that combines dependency shortest paths and subtrees to improve relation classification accuracy, achieving state-of-the-art results on a benchmark dataset.

Contribution

It proposes the augmented dependency path (ADP) structure and dependency-based neural networks (DepNN), integrating recursive and convolutional neural networks for enhanced relation classification.

Findings

Achieved state-of-the-art results on SemEval-2010 dataset.

Effectively models dependency paths and subtrees for relation classification.

Demonstrates the benefit of combining dependency information in neural networks.

Abstract

Previous research on relation classification has verified the effectiveness of using dependency shortest paths or subtrees. In this paper, we further explore how to make full use of the combination of these dependency information. We first propose a new structure, termed augmented dependency path (ADP), which is composed of the shortest dependency path between two entities and the subtrees attached to the shortest path. To exploit the semantic representation behind the ADP structure, we develop dependency-based neural networks (DepNN): a recursive neural network designed to model the subtrees, and a convolutional neural network to capture the most important features on the shortest path. Experiments on the SemEval-2010 dataset show that our proposed method achieves state-of-art results.