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.
Complete list of metadatas

https://hal.inria.fr/hal-01426754
Contributor : Héctor Martínez Alonso <>
Submitted on : Wednesday, January 4, 2017 - 7:34:10 PM
Last modification on : Wednesday, June 12, 2019 - 3:30:03 PM
Long-term archiving on : Wednesday, April 5, 2017 - 3:30:16 PM

File

Q16-1022.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01426754, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

226

Files downloads

269