Skip to main navigation menu Skip to main content Skip to site footer

Vol. 4 (2016)

TACL approved

Multilingual Projection for Parsing Truly Low-Resource Languages

Published 2016-07-13

  • Željko Agić
    • ,
  • Anders Johannsen
    • ,
  • Barbara Plank
    • ,
  • Héctor Martínez Alonso
    • ,
  • Natalie Schluter
    • ,
  • Anders Søgaard

Željko Agić
University of Copenhagen

Anders Johannsen
University of Copenhagen

Barbara Plank
University of Copenhagen

Héctor Martínez Alonso
University of Copenhagen University of Paris 7

Natalie Schluter
University of Copenhagen

Anders Søgaard
University of Copenhagen

Abstract

We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages. Our annotation projection-based approach yields tagging and parsing models for over 100 languages. All that is needed are freely available parallel texts, and taggers and parsers for resource-rich languages. The empirical evaluation across 30 test languages shows that our method consistently provides top-level accuracies, close to established upper bounds, and outperforms several competitive baselines.

PDF (presented at ACL 2016)