Integrating Graph-Based and Transition-Based Dependency Parsers

Previous studies of data-driven dependency parsing have shown that the distribution of parsing errors are correlated with theoretical properties of the models used for learning and inference. In this paper, we show how these results can be exploited to improve parsing accuracy by integrating a graph-based and a transition-based model. By letting one model generate features for the other, we consistently improve accuracy for both models, resulting in a significant improvement of the state of the art when evaluated on data sets from the CoNLL-X shared task.

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Joakim Nivre, Ryan T. McDonald
• Keywords: ACL 2008, Computational Linguistics, Data-driven Dependency, Model Generate Features, Parsing