Work

Multilingual Projection for Parsing Truly Low-Resource Languages

Year: 2016

Type: article

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.

Source: Transactions of the Association for Computational Linguistics

DOI: 10.1162/tacl_a_00100

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