Normal view MARC view ISBD view

Treebank Translation for Cross-Lingual Parser Induction / Tiedemann, Jörg ; Agić, Željko ; Nivre, Joakim.

By: Tiedemann, Jörg.
Contributor(s): Nivre, Joakim [aut] | Agić, Željko [aut].
Material type: ArticleArticleDescription: 130-140 str.Other title: Treebank Translation for Cross-Lingual Parser Induction [Naslov na engleskom:].Subject(s): 5.04 | treebank translation, cross-lingual parsing, parser induction hrv | treebank translation, cross-lingual parsing, parser induction engOnline resources: Click here to access online | Click here to access online In: Eighteenth Conference on Computational Natural Language Learning (CoNLL 2014) (26-27.06.2014 ; Baltimore, SAD) Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL 2014) str. 130-140Summary: Cross-lingual learning has become a popular approach to facilitate the development of resources and tools for low density languages. Its underlying idea is to make use of existing tools and annotations in resource-rich languages to create similar tools and resources for resource-poor languages. Typically, this is achieved by either projecting annotations across parallel corpora, or by transferring models from one or more source languages to a target language. In this paper, we explore a third strategy by using machine translation to create synthetic training data from the original source-side annotations. Specifically, we apply this technique to dependency parsing, using a cross-lingually unified treebank for adequate evaluation. Our approach draws on annotation projection but avoids the use of noisy source-side annotation of an unrelated parallel corpus and instead relies on manual treebank annotation in combination with statistical machine translation, which makes it possible to train fully lexicalized parsers. We show that this approach significantly outperforms delexicalized transfer parsing.% despite the error-prone translation step.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

Cross-lingual learning has become a popular approach to facilitate the development of resources and tools for low density languages. Its underlying idea is to make use of existing tools and annotations in resource-rich languages to create similar tools and resources for resource-poor languages. Typically, this is achieved by either projecting annotations across parallel corpora, or by transferring models from one or more source languages to a target language. In this paper, we explore a third strategy by using machine translation to create synthetic training data from the original source-side annotations. Specifically, we apply this technique to dependency parsing, using a cross-lingually unified treebank for adequate evaluation. Our approach draws on annotation projection but avoids the use of noisy source-side annotation of an unrelated parallel corpus and instead relies on manual treebank annotation in combination with statistical machine translation, which makes it possible to train fully lexicalized parsers. We show that this approach significantly outperforms delexicalized transfer parsing.% despite the error-prone translation step.

Projekt MZOS 130-1300646-1776

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha

//