A Dependency-Based Neural Network for Relation Classification
This work addresses relation classification, a key task in natural language processing, by integrating dependency information more effectively, though it appears incremental as it builds on existing dependency-based methods.
The paper tackles relation classification by proposing an augmented dependency path (ADP) structure that combines shortest dependency paths and subtrees, and develops dependency-based neural networks (DepNN) to model this structure, achieving state-of-the-art results on the SemEval-2010 dataset.
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.