Cross-Lingual Dependency Parsing with Universal Dependencies and Predicted PoS Labels

Abstract

This paper presents cross-lingual models for dependency parsing using the first release of the universal dependencies data set. We systematically compare annotation projection with monolingual baseline models and study the effect of predicted PoS labels in evaluation. Our results reveal the strong impact of tagging accuracy especially with models trained on… (More)

Topics

17 Figures and Tables

Statistics

050100201520162017
Citations per Year

Citation Velocity: 24

Averaging 24 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@inproceedings{Tiedemann2015CrossLingualDP, title={Cross-Lingual Dependency Parsing with Universal Dependencies and Predicted PoS Labels}, author={J{\"o}rg Tiedemann}, booktitle={DepLing}, year={2015} }