Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F14%3A10289240" target="_blank" >RIV/00216208:11320/14:10289240 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Multilingual Dependency Parsing: Using Machine Translated Texts instead of Parallel Corpora
Original language description
This paper revisits the projection-based approach to dependency grammar induction task. Traditional cross-lingual dependency induction tasks one way or the other, depend on the existence of bitexts or target language tools such as part-of-speech (POS) taggers to obtain reasonable parsing accuracy. In this paper, we transfer dependency parsers using only approximate resources, i.e., machine translated bitexts instead of manually created bitexts. We do this by obtaining the the source side of the text from a machine translation (MT) system and then apply transfer approaches to induce parser for the target languages. We further reduce the need for the availability of labeled target language resources by using unsupervised target tagger. We show that our approach consistently outperforms unsupervised parsers by a bigger margin (8.2% absolute), and results in similar performance when compared with delexicalized transfer parsers.
Czech name
—
Czech description
—

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
AI - Linguistics
OECD FORD branch
—

Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)