Paper: Dependency Parsing As A Classication Problem

ACL ID W06-2938
Title Dependency Parsing As A Classication Problem
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2006

This paper presents an approach to depen- dency parsing which can utilize any stan- dard machine learning (classi cation) al- gorithm. A decision list learner was used in this work. The training data provided in the form of a treebank is converted to a format in which each instance represents information about one word pair, and the classi cation indicates the existence, di- rection, and type of the link between the words of the pair. Several distinct mod- els are built to identify the links between word pairs at different distances. These models are applied sequentially to give the dependency parse of a sentence, favoring shorter links. An analysis of the errors, attribute selection, and comparison of dif- ferent languages is presented.