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

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

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 noisy projected data sets.This paper quantifies the differences that can be observed when replacing gold standard labels and our results should influence application developers that rely on crosslingual models that are not tested in realistic scenarios.
Original languageOther/Unknown
Title of host publicationProceedings of the Third International Conference on Dependency Linguistics (Depling 2015)
Number of pages10
Place of PublicationUppsala
PublisherUppsala University
Publication date1 Aug 2015
Pages340-349
Publication statusPublished - 1 Aug 2015
Externally publishedYes
MoE publication typeA4 Article in conference proceedings
EventInternational conference on dependency linguistics - Uppsala, Sweden
Duration: 24 Aug 201526 Aug 2015
Conference number: 3

Fields of Science

  • 6121 Languages

Cite this