Paper: Utilizing Dependency Language Models for Graph-based Dependency Parsing Models

ACL ID P12-1023
Title Utilizing Dependency Language Models for Graph-based Dependency Parsing Models
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

Most previous graph-based parsing models in- crease decoding complexity when they use high-order features due to exact-inference de- coding. In this paper, we present an approach to enriching high-order feature representations for graph-based dependency parsing models using a dependency language model and beam search. The dependency language model is built on a large-amount of additional auto- parsed data that is processed by a baseline parser. Based on the dependency language model, we represent a set of features for the parsing model. Finally, the features are effi- ciently integrated into the parsing model dur- ing decoding using beam search. Our ap- proach has two advantages. Firstly we utilize rich high-order features defined over a view of large scope and additional large raw cor- pu...