What a Transfer-Based System Brings to the Combination with PBMT

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F15%3A10318175" target="_blank" >RIV/00216208:11320/15:10318175 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

What a Transfer-Based System Brings to the Combination with PBMT

Popis výsledku v původním jazyce

We present a thorough analysis of a combination of a statistical and a transfer-based system for English->Czech translation, Moses and TectoMT. We describe several techniques for inspecting such a system combination which are based both on automatic andmanual evaluation. While TectoMT often produces bad translations, Moses is still able to select the good parts of them. In many cases, TectoMT provides useful novel translations which are otherwise simply unavailable to the statistical component, despitethe very large training data. Our analyses confirm the expected behaviour that TectoMT helps with preserving grammatical agreements and valency requirements, but that it also improves a very diverse set of other phenomena. Interestingly, including the outputs of the transfer-based system in the phrase-based search seems to have a positive effect on the search space. Overall, we find that the components of this combination are complementary and the final system produces significantly bet

Název v anglickém jazyce

What a Transfer-Based System Brings to the Combination with PBMT

Popis výsledku anglicky

We present a thorough analysis of a combination of a statistical and a transfer-based system for English->Czech translation, Moses and TectoMT. We describe several techniques for inspecting such a system combination which are based both on automatic andmanual evaluation. While TectoMT often produces bad translations, Moses is still able to select the good parts of them. In many cases, TectoMT provides useful novel translations which are otherwise simply unavailable to the statistical component, despitethe very large training data. Our analyses confirm the expected behaviour that TectoMT helps with preserving grammatical agreements and valency requirements, but that it also improves a very diverse set of other phenomena. Interestingly, including the outputs of the transfer-based system in the phrase-based search seems to have a positive effect on the search space. Overall, we find that the components of this combination are complementary and the final system produces significantly bet

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Fourth Workshop on Hybrid Approaches to Translation (HyTra)

ISBN

978-1-941643-67-9

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

11-20

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Beijing, China

Datum konání akce

31. 7. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—