Show simple item record

dc.contributor.authorMohamed, Emad
dc.contributor.authorSadat, Fatiha
dc.date.accessioned2019-06-13T11:49:27Z
dc.date.available2019-06-13T11:49:27Z
dc.date.issued2014-11-08
dc.identifier.citationMohamed, E. and Sadat, F. (2014) Hybrid Arabic–French machine translation using syntactic re-ordering and morphological pre-processing, Computer Speech & Language, 32(1), pp. 135-144.en
dc.identifier.issn0885-2308en
dc.identifier.doi10.1016/j.csl.2014.10.007en
dc.identifier.urihttp://hdl.handle.net/2436/622444
dc.descriptionThis is an accepted manuscript of an article published by Elsevier BV in Computer Speech & Language on 08/11/2014, available online: https://doi.org/10.1016/j.csl.2014.10.007 The accepted version of the publication may differ from the final published version.
dc.description.abstractArabic is a highly inflected language and a morpho-syntactically complex language with many differences compared to several languages that are heavily studied. It may thus require good pre-processing as it presents significant challenges for Natural Language Processing (NLP), specifically for Machine Translation (MT). This paper aims to examine how Statistical Machine Translation (SMT) can be improved using rule-based pre-processing and language analysis. We describe a hybrid translation approach coupling an Arabic–French statistical machine translation system using the Moses decoder with additional morphological rules that reduce the morphology of the source language (Arabic) to a level that makes it closer to that of the target language (French). Moreover, we introduce additional swapping rules for a structural matching between the source language and the target language. Two structural changes involving the positions of the pronouns and verbs in both the source and target languages have been attempted. The results show an improvement in the quality of translation and a gain in terms of BLEU score after introducing a pre-processing scheme for Arabic and applying these rules based on morphological variations and verb re-ordering (VS into SV constructions) in the source language (Arabic) according to their positions in the target language (French). Furthermore, a learning curve shows the improvement in terms on BLEU score under scarce- and large-resources conditions. The proposed approach is completed without increasing the amount of training data or radically changing the algorithms that can affect the translation or training engines.en
dc.description.sponsorshipThis paper is based upon work supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant number 356097-08.en
dc.formatapplication/PDFen
dc.languageen
dc.language.isoenen
dc.publisherElsevier BVen
dc.relation.urlhttps://www.sciencedirect.com/science/article/pii/S0885230814001065?via%3Dihuben
dc.subjectmachine translationen
dc.subjectlinguistic analysisen
dc.subjectArabic morphologyen
dc.subjectBLEUen
dc.subjectMosesen
dc.subjectArabic–French statistical machine translationen
dc.titleHybrid Arabic–French machine translation using syntactic re-ordering and morphological pre-processingen
dc.typeJournal articleen
dc.identifier.journalComputer Speech & Languageen
dc.date.updated2019-06-04T21:00:36Z
dc.date.accepted2014-10-30
rioxxterms.funderUniversity of Wolverhamptonen
rioxxterms.identifier.projectUOW130619EMen
rioxxterms.versionAMen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
rioxxterms.licenseref.startdate2019-06-13en
dc.source.volume32
dc.source.issue1
dc.source.beginpage135
dc.source.endpage144
dc.description.versionPublished version
refterms.dateFCD2019-06-13T11:49:18Z
refterms.versionFCDAM
refterms.dateFOA2019-06-13T11:49:27Z


Files in this item

Thumbnail
Name:
Publisher version
Thumbnail
Name:
Hybrid_Arabic_French_machine_t ...
Size:
1.744Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by-nc-nd/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc-nd/4.0/