Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F12%3A10130091" target="_blank" >RIV/00216208:11320/12:10130091 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.aclweb.org/anthology-new/W/W12/W12-4205.pdf" target="_blank" >http://www.aclweb.org/anthology-new/W/W12/W12-4205.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors

Popis výsledku v původním jazyce

In this paper, we present two dependency parser training methods appropriate for parsing outputs of statistical machine translation (SMT), which pose problems to standard parsers due to their frequent ungrammaticality. We adapt the MST parser by exploiting additional features from the source language, and by introducing artificial grammatical errors in the parser training data, so that the training sentences resemble SMT output. We evaluate the modified parser on DEPFIX, a system that improves English-Czech SMT outputs using automatic rule-based corrections of grammatical mistakes which requires parsed SMT output sentences as its input. Both parser modifications led to improvements in BLEU score; their combination was evaluated manually, showing a statistically significant improvement of the translation quality.

Název v anglickém jazyce

Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors

Popis výsledku anglicky

In this paper, we present two dependency parser training methods appropriate for parsing outputs of statistical machine translation (SMT), which pose problems to standard parsers due to their frequent ungrammaticality. We adapt the MST parser by exploiting additional features from the source language, and by introducing artificial grammatical errors in the parser training data, so that the training sentences resemble SMT output. We evaluate the modified parser on DEPFIX, a system that improves English-Czech SMT outputs using automatic rule-based corrections of grammatical mistakes which requires parsed SMT output sentences as its input. Both parser modifications led to improvements in BLEU score; their combination was evaluated manually, showing a statistically significant improvement of the translation quality.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/GD201%2F09%2FH057" target="_blank" >GD201/09/H057: Res Informatica</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2012

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-6), ACL

ISBN

978-1-937284-38-1

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

39-48

Název nakladatele

Association for Computational Linguistics

Místo vydání

Jeju, Korea

Místo konání akce

Jeju, Korea

Datum konání akce

12. 7. 2012

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—