Abstract
We develop dependency parsers for Arabic, English, Chinese, and Czech using Bayes Point Machines, a training algorithm which is as easy to implement as the perceptron yet competitive with large margin methods. We achieve results comparable to state-of-the-art in English and Czech, and report the first directed dependency parsing accuracies for Arabic and Chinese. Given the multilingual nature of our experiments, we discuss some issues regarding the comparison of dependency parsers for different languages. © 2006 Association for Computational Linguistics.
Cite
CITATION STYLE
Corston-Oliver, S., Aue, A., Duh, K., & Ringger, E. (2006). Multilingual dependency parsing using bayes point machines. In HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference (pp. 160–167). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1220835.1220856
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
