Simon Corston-Oliver and Anthony Aue

Microsoft Research

(Joint work with Kevin Duh and Eric Ringger)

Multilingual Dependency Parsing using Bayes Point Machines

UW/Microsoft Symposium, 4/07/06

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.

Back to symposium main page