An Augmented Three-Pass System Combination Framework: DCU Combination System for WMT 2010.

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F10%3A10078003" target="_blank" >RIV/00216208:11320/10:10078003 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

An Augmented Three-Pass System Combination Framework: DCU Combination System for WMT 2010.

Popis výsledku v původním jazyce

This paper describes the augmented threepass system combination framework of the Dublin City University (DCU) MT group for the WMT 2010 system combination task. The basic three-pass framework includes building individual confusion networks (CNs), a supernetwork, and a modi?ed Minimum Bayes-risk (mConMBR) decoder. The augmented parts for WMT2010 tasks include 1) a rescoring component which is used to re-rank the N-best lists generated from the individual CNs and the super network, 2) a new hypothesis alignment metric - TERp - that is used to carry out English-targeted hypothesis alignment, and 3) more different backbone-based CNs which are employed to increase the diversity of the mConMBR decoding phase. We took part in the combination tasks of Englishto-Czech and French-to-English. Experimental results show that our proposed combination framework achieved 2.17 absolute points (13.36 relative points) and 1.52 absolute points (5.37 relative points) in terms of BLEU score on English-toCz

Název v anglickém jazyce

An Augmented Three-Pass System Combination Framework: DCU Combination System for WMT 2010.

Popis výsledku anglicky

This paper describes the augmented threepass system combination framework of the Dublin City University (DCU) MT group for the WMT 2010 system combination task. The basic three-pass framework includes building individual confusion networks (CNs), a supernetwork, and a modi?ed Minimum Bayes-risk (mConMBR) decoder. The augmented parts for WMT2010 tasks include 1) a rescoring component which is used to re-rank the N-best lists generated from the individual CNs and the super network, 2) a new hypothesis alignment metric - TERp - that is used to carry out English-targeted hypothesis alignment, and 3) more different backbone-based CNs which are employed to increase the diversity of the mConMBR decoding phase. We took part in the combination tasks of Englishto-Czech and French-to-English. Experimental results show that our proposed combination framework achieved 2.17 absolute points (13.36 relative points) and 1.52 absolute points (5.37 relative points) in terms of BLEU score on English-toCz

Druh

D - Stať ve sborníku

CEP obor

AI - Jazykověda

OECD FORD obor

—

Projekt

<a href="/cs/project/GA405%2F09%2F0278" target="_blank" >GA405/09/0278: Internet jako jazykový korpus</a><br>

Návaznosti

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

Rok uplatnění

2010

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR

ISBN

978-1-932432-71-8

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

—

Název nakladatele

Association for Computational Linguistics

Místo vydání

Uppsala, Sweden

Místo konání akce

Uppsala, Sweden

Datum konání akce

15. 7. 2010

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—