Deeper Machine Translation and Evaluation for German

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10372124" target="_blank" >RIV/00216208:11320/16:10372124 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Deeper Machine Translation and Evaluation for German

Popis výsledku v původním jazyce

This paper describes a hybrid Machine Translation (MT) system built for translating from English to German in the domain of technical documentation. The system is based on three different MT engines (phrase-based SMT, RBMT, neural) that are joined by a selection mechanism that uses deep linguistic features within a machine learning process. It also presents a detailed source-driven manual error analysis we have performed using a dedicated &quot;test suite&quot; that contains selected examples of relevant phenomena. While automatic scores show huge differences between the engines, the overall average number or errors they (do not) make is very similar for all systems. However, the detailed error breakdown shows that the systems behave very differently concerning the various phenomena.

Název v anglickém jazyce

Deeper Machine Translation and Evaluation for German

Popis výsledku anglicky

This paper describes a hybrid Machine Translation (MT) system built for translating from English to German in the domain of technical documentation. The system is based on three different MT engines (phrase-based SMT, RBMT, neural) that are joined by a selection mechanism that uses deep linguistic features within a machine learning process. It also presents a detailed source-driven manual error analysis we have performed using a dedicated &quot;test suite&quot; that contains selected examples of relevant phenomena. While automatic scores show huge differences between the engines, the overall average number or errors they (do not) make is very similar for all systems. However, the detailed error breakdown shows that the systems behave very differently concerning the various phenomena.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

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 2nd Deep Machine Translation Workshop

ISBN

978-80-88132-02-8

ISSN

—

e-ISSN

neuvedeno

Počet stran výsledku

10

Strana od-do

29-38

Název nakladatele

ÚFAL MFF UK

Místo vydání

Praha, Czechia

Místo konání akce

Lisboa, Portugal

Datum konání akce

21. 10. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—