A Dependency-Based Neural Network for Relation Classification
arXiv:1507.04646
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.
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)
References in corpus (1)
Cited by in corpus (8)
- Classifying medical relations in clinical text via convolutional neural networks
- Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
- Structural block driven - enhanced convolutional neural representation for relation extraction
- Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
- Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation
- Efficient long-distance relation extraction with DG-SpanBERT
- Feature Assisted bi-directional LSTM Model for Protein-Protein Interaction Identification from Biomedical Texts
- On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning