Multilingual Projection for Parsing Truly Low-Resource Languageš - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Transactions of the Association for Computational Linguistics Year : 2016

Multilingual Projection for Parsing Truly Low-Resource Languageš

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.
Fichier principal
Vignette du fichier
Q16-1022.pdf (305.42 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01426754 , version 1 (04-01-2017)

Identifiers

  • HAL Id : hal-01426754 , version 1

Cite

Zeljko Agic, Anders Johannsen, Barbara Plank, Héctor Martínez Alonso, Natalie Schluter, et al.. Multilingual Projection for Parsing Truly Low-Resource Languageš. Transactions of the Association for Computational Linguistics, 2016. ⟨hal-01426754⟩
123 View
363 Download

Share

Gmail Facebook X LinkedIn More