A dependency-based neural network for relation classification

Abstract

Previous research on relation classification has verified the effectiveness of using de-pendency shortest paths or subtrees. In this paper, we further explore how to make full use of the combination of these de-pendency information. We first propose a new structure, termed augmented de-pendency 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 net-works (DepNN): a recursive neural net-work 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.