Cargando…

Machine translation with minimal reliance on parallel resources

This book provides a unified view on a new methodology for Machine Translation (MT). This methodology extracts information from widely available resources (extensive monolingual corpora) while only assuming the existence of a very limited parallel corpus, thus having a unique starting point to Stati...

Descripción completa

Detalles Bibliográficos
Autores principales: Tambouratzis, George, Vassiliou, Marina, Sofianopoulos, Sokratis
Lenguaje:eng
Publicado: Springer 2017
Materias:
Acceso en línea:https://dx.doi.org/10.1007/978-3-319-63107-3
http://cds.cern.ch/record/2282079
_version_ 1780955619383050240
author Tambouratzis, George
Vassiliou, Marina
Sofianopoulos, Sokratis
author_facet Tambouratzis, George
Vassiliou, Marina
Sofianopoulos, Sokratis
author_sort Tambouratzis, George
collection CERN
description This book provides a unified view on a new methodology for Machine Translation (MT). This methodology extracts information from widely available resources (extensive monolingual corpora) while only assuming the existence of a very limited parallel corpus, thus having a unique starting point to Statistical Machine Translation (SMT). In this book, a detailed presentation of the methodology principles and system architecture is followed by a series of experiments, where the proposed system is compared to other MT systems using a set of established metrics including BLEU, NIST, Meteor and TER. Additionally, a free-to-use code is available, that allows the creation of new MT systems. The volume is addressed to both language professionals and researchers. Prerequisites for the readers are very limited and include a basic understanding of the machine translation as well as of the basic tools of natural language processing.
id cern-2282079
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2017
publisher Springer
record_format invenio
spelling cern-22820792021-04-21T19:05:07Zdoi:10.1007/978-3-319-63107-3http://cds.cern.ch/record/2282079engTambouratzis, GeorgeVassiliou, MarinaSofianopoulos, SokratisMachine translation with minimal reliance on parallel resourcesMathematical Physics and MathematicsThis book provides a unified view on a new methodology for Machine Translation (MT). This methodology extracts information from widely available resources (extensive monolingual corpora) while only assuming the existence of a very limited parallel corpus, thus having a unique starting point to Statistical Machine Translation (SMT). In this book, a detailed presentation of the methodology principles and system architecture is followed by a series of experiments, where the proposed system is compared to other MT systems using a set of established metrics including BLEU, NIST, Meteor and TER. Additionally, a free-to-use code is available, that allows the creation of new MT systems. The volume is addressed to both language professionals and researchers. Prerequisites for the readers are very limited and include a basic understanding of the machine translation as well as of the basic tools of natural language processing.Springeroai:cds.cern.ch:22820792017
spellingShingle Mathematical Physics and Mathematics
Tambouratzis, George
Vassiliou, Marina
Sofianopoulos, Sokratis
Machine translation with minimal reliance on parallel resources
title Machine translation with minimal reliance on parallel resources
title_full Machine translation with minimal reliance on parallel resources
title_fullStr Machine translation with minimal reliance on parallel resources
title_full_unstemmed Machine translation with minimal reliance on parallel resources
title_short Machine translation with minimal reliance on parallel resources
title_sort machine translation with minimal reliance on parallel resources
topic Mathematical Physics and Mathematics
url https://dx.doi.org/10.1007/978-3-319-63107-3
http://cds.cern.ch/record/2282079
work_keys_str_mv AT tambouratzisgeorge machinetranslationwithminimalrelianceonparallelresources
AT vassilioumarina machinetranslationwithminimalrelianceonparallelresources
AT sofianopoulossokratis machinetranslationwithminimalrelianceonparallelresources