Normal view MARC view ISBD view

Multilingual projection for parsing truly low-resource languages / Agić, Željko ; Johannsen, Anders ; Plank, Barbara ; Alonso Martínez, Héctor ; Schluter, Natalie ; Søgaard, Anders.

By: Agić, Željko.
Contributor(s): Johannsen, Anders [aut] | Plank, Barbara [aut] | Alonso Martínez, Héctor [aut] | Schluter, Natalie [aut] | Søgaard, Anders [aut].
Material type: ArticleArticlePublisher: 2016Description: 301-312 str.Other title: Multilingual projection for parsing truly low-resource languages [Naslov na engleskom:].Subject(s): 2.09 | dependency parsing ; cross-lingual ; low-resource languages | dependency parsing ; cross-lingual ; low-resource languagesOnline resources: Click here to access online | Click here to access online In: Transactions of the Association for Computational Linguistics 4 (2016) ; str. 301-312Summary: 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.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

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.

Projekt MZOS projekt

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha

//