Translation rules and ANN based model for english to urdu machine translation

Detalhes bibliográficos
Autor(a) principal: Shahnawaz, Ahmad
Data de Publicação: 2011
Outros Autores: Mishra, R. B.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFLA
Texto Completo: http://www.dcc.ufla.br/infocomp/index.php/INFOCOMP/article/view/336
http://repositorio.ufla.br/jspui/handle/1/14988
Resumo: In this paper we discuss the working of our English to Urdu Machine Translation (MT) system. We used feed-forward back-propagation artificial neural network for the selection of Urdu words/tokens (such as verb, noun/pronoun etc.) and translation rules for grammar structure equivalent to English words/tokens and grammar structure rules respectively. As English is SVO class language while Urdu is SOV class language so grammar structure transfer is main task in English-Urdu machine translation problem. Our system is able to translate sentences having gerund, having infinitives (maximum two), having prepositions and prepositional objects (maximum three), direct object, indirect object etc. Neural network works as the knowledge base for linguistic rules and bilingual dictionary. Bilingual dictionary not only stores the meaning of English word in Urdu but also stores linguistic features attached to the word. The output of our system is presented in Romanized Urdu. The n-gram blue score achieved by the system is 0.6954; METEOR score achieved is 0.8583 and F-score of 0.8650.
id UFLA_dbf017b9f4d765079357aa6b07861197
oai_identifier_str oai:localhost:1/14988
network_acronym_str UFLA
network_name_str Repositório Institucional da UFLA
repository_id_str
spelling Translation rules and ANN based model for english to urdu machine translationNeural networkBack-propagationRule based translationMachine translation systemArtificial IntelligenceIn this paper we discuss the working of our English to Urdu Machine Translation (MT) system. We used feed-forward back-propagation artificial neural network for the selection of Urdu words/tokens (such as verb, noun/pronoun etc.) and translation rules for grammar structure equivalent to English words/tokens and grammar structure rules respectively. As English is SVO class language while Urdu is SOV class language so grammar structure transfer is main task in English-Urdu machine translation problem. Our system is able to translate sentences having gerund, having infinitives (maximum two), having prepositions and prepositional objects (maximum three), direct object, indirect object etc. Neural network works as the knowledge base for linguistic rules and bilingual dictionary. Bilingual dictionary not only stores the meaning of English word in Urdu but also stores linguistic features attached to the word. The output of our system is presented in Romanized Urdu. The n-gram blue score achieved by the system is 0.6954; METEOR score achieved is 0.8583 and F-score of 0.8650.Universidade Federal de Lavras (UFLA)2011-09-012017-08-01T21:08:43Z2017-08-01T21:08:43Z2017-08-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://www.dcc.ufla.br/infocomp/index.php/INFOCOMP/article/view/336SHAHNAWAZ, A.; MISHRA, R. B. Translation rules and ANN based model for english to urdu machine translation. INFOCOMP Journal of Computer Science, Lavras, v. 10, n. 3, p. 25-35, Sept. 2011.http://repositorio.ufla.br/jspui/handle/1/14988INFOCOMP; Vol 10 No 3 (2011): September, 2011; 25-351982-33631807-4545reponame:Repositório Institucional da UFLAinstname:Universidade Federal de Lavras (UFLA)instacron:UFLAenghttp://www.dcc.ufla.br/infocomp/index.php/INFOCOMP/article/view/336/320Copyright (c) 2016 INFOCOMP Journal of Computer Scienceinfo:eu-repo/semantics/openAccessShahnawaz, AhmadMishra, R. B.2021-09-24T23:36:36Zoai:localhost:1/14988Repositório InstitucionalPUBhttp://repositorio.ufla.br/oai/requestnivaldo@ufla.br || repositorio.biblioteca@ufla.bropendoar:2021-09-24T23:36:36Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)false
dc.title.none.fl_str_mv Translation rules and ANN based model for english to urdu machine translation
title Translation rules and ANN based model for english to urdu machine translation
spellingShingle Translation rules and ANN based model for english to urdu machine translation
Shahnawaz, Ahmad
Neural network
Back-propagation
Rule based translation
Machine translation system
Artificial Intelligence
title_short Translation rules and ANN based model for english to urdu machine translation
title_full Translation rules and ANN based model for english to urdu machine translation
title_fullStr Translation rules and ANN based model for english to urdu machine translation
title_full_unstemmed Translation rules and ANN based model for english to urdu machine translation
title_sort Translation rules and ANN based model for english to urdu machine translation
author Shahnawaz, Ahmad
author_facet Shahnawaz, Ahmad
Mishra, R. B.
author_role author
author2 Mishra, R. B.
author2_role author
dc.contributor.author.fl_str_mv Shahnawaz, Ahmad
Mishra, R. B.
dc.subject.por.fl_str_mv Neural network
Back-propagation
Rule based translation
Machine translation system
Artificial Intelligence
topic Neural network
Back-propagation
Rule based translation
Machine translation system
Artificial Intelligence
description In this paper we discuss the working of our English to Urdu Machine Translation (MT) system. We used feed-forward back-propagation artificial neural network for the selection of Urdu words/tokens (such as verb, noun/pronoun etc.) and translation rules for grammar structure equivalent to English words/tokens and grammar structure rules respectively. As English is SVO class language while Urdu is SOV class language so grammar structure transfer is main task in English-Urdu machine translation problem. Our system is able to translate sentences having gerund, having infinitives (maximum two), having prepositions and prepositional objects (maximum three), direct object, indirect object etc. Neural network works as the knowledge base for linguistic rules and bilingual dictionary. Bilingual dictionary not only stores the meaning of English word in Urdu but also stores linguistic features attached to the word. The output of our system is presented in Romanized Urdu. The n-gram blue score achieved by the system is 0.6954; METEOR score achieved is 0.8583 and F-score of 0.8650.
publishDate 2011
dc.date.none.fl_str_mv 2011-09-01
2017-08-01T21:08:43Z
2017-08-01T21:08:43Z
2017-08-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://www.dcc.ufla.br/infocomp/index.php/INFOCOMP/article/view/336
SHAHNAWAZ, A.; MISHRA, R. B. Translation rules and ANN based model for english to urdu machine translation. INFOCOMP Journal of Computer Science, Lavras, v. 10, n. 3, p. 25-35, Sept. 2011.
http://repositorio.ufla.br/jspui/handle/1/14988
url http://www.dcc.ufla.br/infocomp/index.php/INFOCOMP/article/view/336
http://repositorio.ufla.br/jspui/handle/1/14988
identifier_str_mv SHAHNAWAZ, A.; MISHRA, R. B. Translation rules and ANN based model for english to urdu machine translation. INFOCOMP Journal of Computer Science, Lavras, v. 10, n. 3, p. 25-35, Sept. 2011.
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv http://www.dcc.ufla.br/infocomp/index.php/INFOCOMP/article/view/336/320
dc.rights.driver.fl_str_mv Copyright (c) 2016 INFOCOMP Journal of Computer Science
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2016 INFOCOMP Journal of Computer Science
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade Federal de Lavras (UFLA)
publisher.none.fl_str_mv Universidade Federal de Lavras (UFLA)
dc.source.none.fl_str_mv INFOCOMP; Vol 10 No 3 (2011): September, 2011; 25-35
1982-3363
1807-4545
reponame:Repositório Institucional da UFLA
instname:Universidade Federal de Lavras (UFLA)
instacron:UFLA
instname_str Universidade Federal de Lavras (UFLA)
instacron_str UFLA
institution UFLA
reponame_str Repositório Institucional da UFLA
collection Repositório Institucional da UFLA
repository.name.fl_str_mv Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)
repository.mail.fl_str_mv nivaldo@ufla.br || repositorio.biblioteca@ufla.br
_version_ 1784550168380571648

Registros relacionados