Abstract
We describe a parser used in the CoNLL 2006 Shared Task, "Multingual Dependency Parsing." The parser first identifies syntactic dependencies and then labels those dependencies using a maximum entropy classifier. We consider the impact of feature engineering and the choice of machine learning algorithm, with particular focus on Slovene, Spanish and Swedish.
Cite
CITATION STYLE
Corston-Oliver, S., & Aue, A. (2006). Dependency parsing with reference to Slovene, Spanish and Swedish. In Proceedings of the Tenth Conference on Computational Natural Language Learning, CoNLL-X. Association for Computational Linguistics (ACL). https://doi.org/10.3115/1596276.1596313
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.