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.
- Pub Date:
- July 2015
- Computer Science - Computation and Language;
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing
- This preprint is the full version of a short paper accepted in the annual meeting of the Association for Computational Linguistics (ACL) 2015 (Beijing, China)