Classical Arabic English machine translation using rule-based approach

Huda Alhusain Hebresha, Mohd Juzaiddin Ab Aziz

Research output: Contribution to journalArticle

Abstract

Arabic machine translation has been taking place in machine translation projects during last decade and so, many projects have been carried out to enhance the quality of translation from and into Arabic. This research concentrates on the translation of Classical Arabic (CA) rather than Modern Standard Arabic. The challenges of this research are the difficulty of delivering the appropriate meaning of the CA terms in the target language (English), different sentence structure between two languages, word agreement and ordering problem. Focusing on these issues, the research purpose was to create an automatic translation system to translate text from CA into English using Rule-based approach. The developed system Classical Arabic Machine Translation (CAMT) involves three phases which are: analysis, transfer and generation. In the analysis phase the CA input text is analyzed morphologically and syntactically. The transfer stage includes constructing reasonable rule of the CA input text structure and its equivalent rule in the target language (English). In the final phase, the Arabic source text will be generated to obtain the target text in English. The evaluation process is done by comparing the output produced by our system with the original human translation using İBLEU metric. An accuracy of 89.4% was the results produced by İBLEU algorithm, which prove that using Rule-based approach provides good results in translating CA into English.

Original languageEnglish
Pages (from-to)79-86
Number of pages8
JournalJournal of Applied Sciences
Volume13
Issue number1
DOIs
Publication statusPublished - 2013

Keywords

  • Automatic evaluation of MT
  • Classical arabic language
  • English language
  • Machine translation
  • Morphological analysis
  • Rule-based approach
  • Sentence structure

ASJC Scopus subject areas

  • General

Cite this

Classical Arabic English machine translation using rule-based approach. / Hebresha, Huda Alhusain; Ab Aziz, Mohd Juzaiddin.

In: Journal of Applied Sciences, Vol. 13, No. 1, 2013, p. 79-86.

Research output: Contribution to journalArticle

@article{e45d13d4e46e47eab1279c2f84ca231d,
title = "Classical Arabic English machine translation using rule-based approach",
abstract = "Arabic machine translation has been taking place in machine translation projects during last decade and so, many projects have been carried out to enhance the quality of translation from and into Arabic. This research concentrates on the translation of Classical Arabic (CA) rather than Modern Standard Arabic. The challenges of this research are the difficulty of delivering the appropriate meaning of the CA terms in the target language (English), different sentence structure between two languages, word agreement and ordering problem. Focusing on these issues, the research purpose was to create an automatic translation system to translate text from CA into English using Rule-based approach. The developed system Classical Arabic Machine Translation (CAMT) involves three phases which are: analysis, transfer and generation. In the analysis phase the CA input text is analyzed morphologically and syntactically. The transfer stage includes constructing reasonable rule of the CA input text structure and its equivalent rule in the target language (English). In the final phase, the Arabic source text will be generated to obtain the target text in English. The evaluation process is done by comparing the output produced by our system with the original human translation using İBLEU metric. An accuracy of 89.4{\%} was the results produced by İBLEU algorithm, which prove that using Rule-based approach provides good results in translating CA into English.",
keywords = "Automatic evaluation of MT, Classical arabic language, English language, Machine translation, Morphological analysis, Rule-based approach, Sentence structure",
author = "Hebresha, {Huda Alhusain} and {Ab Aziz}, {Mohd Juzaiddin}",
year = "2013",
doi = "10.3923/jas.2013.79.86",
language = "English",
volume = "13",
pages = "79--86",
journal = "Journal of Applied Sciences",
issn = "1812-5654",
publisher = "Asian Network for Scientific Information",
number = "1",

}

TY - JOUR

T1 - Classical Arabic English machine translation using rule-based approach

AU - Hebresha, Huda Alhusain

AU - Ab Aziz, Mohd Juzaiddin

PY - 2013

Y1 - 2013

N2 - Arabic machine translation has been taking place in machine translation projects during last decade and so, many projects have been carried out to enhance the quality of translation from and into Arabic. This research concentrates on the translation of Classical Arabic (CA) rather than Modern Standard Arabic. The challenges of this research are the difficulty of delivering the appropriate meaning of the CA terms in the target language (English), different sentence structure between two languages, word agreement and ordering problem. Focusing on these issues, the research purpose was to create an automatic translation system to translate text from CA into English using Rule-based approach. The developed system Classical Arabic Machine Translation (CAMT) involves three phases which are: analysis, transfer and generation. In the analysis phase the CA input text is analyzed morphologically and syntactically. The transfer stage includes constructing reasonable rule of the CA input text structure and its equivalent rule in the target language (English). In the final phase, the Arabic source text will be generated to obtain the target text in English. The evaluation process is done by comparing the output produced by our system with the original human translation using İBLEU metric. An accuracy of 89.4% was the results produced by İBLEU algorithm, which prove that using Rule-based approach provides good results in translating CA into English.

AB - Arabic machine translation has been taking place in machine translation projects during last decade and so, many projects have been carried out to enhance the quality of translation from and into Arabic. This research concentrates on the translation of Classical Arabic (CA) rather than Modern Standard Arabic. The challenges of this research are the difficulty of delivering the appropriate meaning of the CA terms in the target language (English), different sentence structure between two languages, word agreement and ordering problem. Focusing on these issues, the research purpose was to create an automatic translation system to translate text from CA into English using Rule-based approach. The developed system Classical Arabic Machine Translation (CAMT) involves three phases which are: analysis, transfer and generation. In the analysis phase the CA input text is analyzed morphologically and syntactically. The transfer stage includes constructing reasonable rule of the CA input text structure and its equivalent rule in the target language (English). In the final phase, the Arabic source text will be generated to obtain the target text in English. The evaluation process is done by comparing the output produced by our system with the original human translation using İBLEU metric. An accuracy of 89.4% was the results produced by İBLEU algorithm, which prove that using Rule-based approach provides good results in translating CA into English.

KW - Automatic evaluation of MT

KW - Classical arabic language

KW - English language

KW - Machine translation

KW - Morphological analysis

KW - Rule-based approach

KW - Sentence structure

UR - http://www.scopus.com/inward/record.url?scp=84873257625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873257625&partnerID=8YFLogxK

U2 - 10.3923/jas.2013.79.86

DO - 10.3923/jas.2013.79.86

M3 - Article

VL - 13

SP - 79

EP - 86

JO - Journal of Applied Sciences

JF - Journal of Applied Sciences

SN - 1812-5654

IS - 1

ER -