A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation

A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation

In this paper we present a Neural Network (NN) architecture for detecting grammatical errors in Statistical Machine Translation (SMT) using monolingual morpho-syntactic word representations in combination with surface and syntactic context windows. We test our approach on two language pairs and two...

Full description

Bibliographic Details
Main Authors: Tezcan Arda, Hoste Véronique, Macken Lieve
Format: Article
Language:English
Published: Sciendo 2017-06-01
Series:Prague Bulletin of Mathematical Linguistics
Online Access:https://doi.org/10.1515/pralin-2017-0015
id doaj-9d1b87bbf0114c19a44ed733faa3f661
record_format Article
spelling doaj-9d1b87bbf0114c19a44ed733faa3f6612021-09-05T13:59:53ZengSciendoPrague Bulletin of Mathematical Linguistics 1804-04622017-06-01108113314510.1515/pralin-2017-0015pralin-2017-0015A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine TranslationTezcan Arda0Hoste Véronique1Macken Lieve2LT³, Language and Translation Technology Team, Department of Translation, Interpreting and Communication, Ghent UniversityLT³, Language and Translation Technology Team, Department of Translation, Interpreting and Communication, Ghent UniversityLT³, Language and Translation Technology Team, Department of Translation, Interpreting and Communication, Ghent UniversityIn this paper we present a Neural Network (NN) architecture for detecting grammatical errors in Statistical Machine Translation (SMT) using monolingual morpho-syntactic word representations in combination with surface and syntactic context windows. We test our approach on two language pairs and two tasks, namely detecting grammatical errors and predicting overall post-editing effort. Our results show that this approach is not only able to accurately detect grammatical errors but it also performs well as a quality estimation system for predicting overall post-editing effort, which is characterised by all types of MT errors. Furthermore, we show that this approach is portable to other languages.https://doi.org/10.1515/pralin-2017-0015
collection DOAJ
language English
format Article
sources DOAJ
author Tezcan Arda
Hoste Véronique
Macken Lieve
spellingShingle Tezcan Arda
Hoste Véronique
Macken Lieve
A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
Prague Bulletin of Mathematical Linguistics
author_facet Tezcan Arda
Hoste Véronique
Macken Lieve
author_sort Tezcan Arda
title A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
title_short A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
title_full A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
title_fullStr A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
title_full_unstemmed A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
title_sort neural network architecture for detecting grammatical errors in statistical machine translation
publisher Sciendo
series Prague Bulletin of Mathematical Linguistics
issn 1804-0462
publishDate 2017-06-01
description In this paper we present a Neural Network (NN) architecture for detecting grammatical errors in Statistical Machine Translation (SMT) using monolingual morpho-syntactic word representations in combination with surface and syntactic context windows. We test our approach on two language pairs and two tasks, namely detecting grammatical errors and predicting overall post-editing effort. Our results show that this approach is not only able to accurately detect grammatical errors but it also performs well as a quality estimation system for predicting overall post-editing effort, which is characterised by all types of MT errors. Furthermore, we show that this approach is portable to other languages.
url https://doi.org/10.1515/pralin-2017-0015
work_keys_str_mv AT tezcanarda aneuralnetworkarchitecturefordetectinggrammaticalerrorsinstatisticalmachinetranslation
AT hosteveronique aneuralnetworkarchitecturefordetectinggrammaticalerrorsinstatisticalmachinetranslation
AT mackenlieve aneuralnetworkarchitecturefordetectinggrammaticalerrorsinstatisticalmachinetranslation
AT tezcanarda neuralnetworkarchitecturefordetectinggrammaticalerrorsinstatisticalmachinetranslation
AT hosteveronique neuralnetworkarchitecturefordetectinggrammaticalerrorsinstatisticalmachinetranslation
AT mackenlieve neuralnetworkarchitecturefordetectinggrammaticalerrorsinstatisticalmachinetranslation
_version_ 1717812838924288000

Similar Items