English to Urdu Statistical Machine Translation: Establishing a Baseline

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F14%3A10289379" target="_blank" >RIV/00216208:11320/14:10289379 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

English to Urdu Statistical Machine Translation: Establishing a Baseline

Popis výsledku v původním jazyce

The aim of this paper is to categorize and present the existence of resources for English- to-Urdu machine translation (MT) and to establish an empirical baseline for this task. By doing so, we hope to set up a common ground for MT research with Urdu toallow for a congruent progress in this field. We build baseline phrase-based MT (PBMT) and hierarchical MT systems and report the results on 3 official independent test sets. On all test sets, hierarchial MT significantly outperformed PBMT. The highest single-reference BLEU score is achieved by the hierarchical system and reaches 21.58% but this figure depends on the randomly selected test set. Our manual evaluation of 175 sentences suggests that in 45% of sentences, the hierarchical MT is ranked betterthan the PBMT output compared to 21% of sentences where PBMT wins, the rest being equal.

Název v anglickém jazyce

English to Urdu Statistical Machine Translation: Establishing a Baseline

Popis výsledku anglicky

The aim of this paper is to categorize and present the existence of resources for English- to-Urdu machine translation (MT) and to establish an empirical baseline for this task. By doing so, we hope to set up a common ground for MT research with Urdu toallow for a congruent progress in this field. We build baseline phrase-based MT (PBMT) and hierarchical MT systems and report the results on 3 official independent test sets. On all test sets, hierarchial MT significantly outperformed PBMT. The highest single-reference BLEU score is achieved by the hierarchical system and reaches 21.58% but this figure depends on the randomly selected test set. Our manual evaluation of 175 sentences suggests that in 45% of sentences, the hierarchical MT is ranked betterthan the PBMT output compared to 21% of sentences where PBMT wins, the rest being equal.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

ISBN

978-1-941643-26-6

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

37-42

Název nakladatele

Dublin City University and Association for Computational Linguistics

Místo vydání

Dublin, Ireland

Místo konání akce

Dublin, Ireland

Datum konání akce

23. 8. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—