Merged bilingual trees based on Universal Dependencies in Machine Translation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335495" target="_blank" >RIV/00216208:11320/16:10335495 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclweb.org/anthology/W/W16/W16-2318.pdf" target="_blank" >https://aclweb.org/anthology/W/W16/W16-2318.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Merged bilingual trees based on Universal Dependencies in Machine Translation

Popis výsledku v původním jazyce

In this paper, we present our new experimental system of merging dependency representations of two parallel sentences into one dependency tree. All the inner nodes in dependency tree represent source-target pairs of words, the extra words are in form of leaf nodes. We use Universal Dependencies annotation style, in which the function words, whose usage often differs between languages, are annotated as leaves. The parallel treebank is parsed in minimally supervised way. Unaligned words are there automatically pushed to leaves. We present a simple translation system trained on such merged trees and evaluate it in WMT 2016 English-to-Czech and Czech-to-English translation task. Even though the model is so far very simple and no language model and word-reordering model were used, the Czech-to-English variant reached similar BLEU score as another established tree-based system.

Název v anglickém jazyce

Merged bilingual trees based on Universal Dependencies in Machine Translation

Popis výsledku anglicky

In this paper, we present our new experimental system of merging dependency representations of two parallel sentences into one dependency tree. All the inner nodes in dependency tree represent source-target pairs of words, the extra words are in form of leaf nodes. We use Universal Dependencies annotation style, in which the function words, whose usage often differs between languages, are annotated as leaves. The parallel treebank is parsed in minimally supervised way. Unaligned words are there automatically pushed to leaves. We present a simple translation system trained on such merged trees and evaluate it in WMT 2016 English-to-Czech and Czech-to-English translation task. Even though the model is so far very simple and no language model and word-reordering model were used, the Czech-to-English variant reached similar BLEU score as another established tree-based system.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/GP14-06548P" target="_blank" >GP14-06548P: Odvození větné struktury bez anotovaných korpusů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the First Conference on Machine Translation (WMT). Volume 2: Shared Task Papers

ISBN

978-1-945626-10-4

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

333-338

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Berlin, Germany

Datum konání akce

11. 8. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—