An Effective Neural Network Model for Graph-based Dependency Parsing

Most existing graph-based parsing models rely on millions of hand-crafted features, which limits their generalization ability and slows down the parsing speed. In this paper, we propose a general and effective Neural Network model for graph-based dependency parsing. Our model can automatically learn high-order feature combinations using only atomic features by exploiting a novel activation function tanhcube. Moreover, we propose a simple yet effective way to utilize phrase-level information that is expensive to use in conventional graph-based parsers. Experiments on the English Penn Treebank show that parsers based on our model perform better than conventional graph-based parsers.

• Type: Journal
• Year: 2015
• Where: ACL
• Authors: Wenzhe Pei, Tao Ge, Baobao Chang
• Keywords: ACL 2015, Computational Linguistics