Machine translation of noun phrases from Arabic to english using transfer-based approach

Omar Shirko, Nazlia Omar, Haslina Arshad, Mohammed Albared

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Problem statement: Any Arabic to English Machine Translation (MT) system should be capable of dealing with word order which Arabic exhibits. This poses a significant challenge to MT due to the vast number of ways to express the same sentence in Arabic. The ordering features are very important and should be carefully applied to ensure the generation of sentence in the target language. Because they apply to the target language, it should fulfill the specific requirement of this language. Mistakes in the MT output can be either the result of analysis problems at the source language level, or due to generation problem at target language level. Word order rules are crucial for the generation of sentences in the target language. They also serve as rules for the ordering of sentence constituents. These rules draw their information from the syntactic knowledge. The word order problem becomes more obvious when making machine translation between languages that have rich morphological variations. Approach: The main objective of this research is to develop a machine translation that translates Arabic noun phrases into English by using transfer-based approach. A system called Npae-Rbmt has been developed in this research. Transfer-based machine translation is one instance of rulebased machine-translation approaches and is currently one of the most widely used methods of machine translation. The idea of transfer-based machine translation it is necessary to have an intermediate representation that captures the "meaning" of the original sentence in order to generate the correct translation. Using advantages of transfer-based machine translation such as analysis step, the Transfer-based becomes simpler as linguistic analysis goes deeper-as the representation of analysis step becomes more abstract. In fact, a major goal of MT research is to define a level of analysis which is so deep in which transfer-based machine translation is able to do. Results: The method was tested on 88 thesis titles and journals from the computer science domain. The accuracy of the result was 94.6%. These results proved the viability of this approach for distant languages. Conclusion: Based on the achieved results, we have managed to perform the syntactic reordering within an Arabic noun phrases to English translation task by using transfer-based machine translation and also achieved reasonable improvements in translation quality over related approach.

Original languageEnglish
Pages (from-to)350-356
Number of pages7
JournalJournal of Computer Science
Volume6
Issue number3
Publication statusPublished - 2010

Fingerprint

Syntactics
Linguistics
Computer science

Keywords

  • Arabic language processing
  • Machine translation
  • Noun phrases
  • Npae-Rbmt
  • Transfer-based approach

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Machine translation of noun phrases from Arabic to english using transfer-based approach. / Shirko, Omar; Omar, Nazlia; Arshad, Haslina; Albared, Mohammed.

In: Journal of Computer Science, Vol. 6, No. 3, 2010, p. 350-356.

Research output: Contribution to journalArticle

@article{f54f446b078c42e096a413802446ea0d,
title = "Machine translation of noun phrases from Arabic to english using transfer-based approach",
abstract = "Problem statement: Any Arabic to English Machine Translation (MT) system should be capable of dealing with word order which Arabic exhibits. This poses a significant challenge to MT due to the vast number of ways to express the same sentence in Arabic. The ordering features are very important and should be carefully applied to ensure the generation of sentence in the target language. Because they apply to the target language, it should fulfill the specific requirement of this language. Mistakes in the MT output can be either the result of analysis problems at the source language level, or due to generation problem at target language level. Word order rules are crucial for the generation of sentences in the target language. They also serve as rules for the ordering of sentence constituents. These rules draw their information from the syntactic knowledge. The word order problem becomes more obvious when making machine translation between languages that have rich morphological variations. Approach: The main objective of this research is to develop a machine translation that translates Arabic noun phrases into English by using transfer-based approach. A system called Npae-Rbmt has been developed in this research. Transfer-based machine translation is one instance of rulebased machine-translation approaches and is currently one of the most widely used methods of machine translation. The idea of transfer-based machine translation it is necessary to have an intermediate representation that captures the {"}meaning{"} of the original sentence in order to generate the correct translation. Using advantages of transfer-based machine translation such as analysis step, the Transfer-based becomes simpler as linguistic analysis goes deeper-as the representation of analysis step becomes more abstract. In fact, a major goal of MT research is to define a level of analysis which is so deep in which transfer-based machine translation is able to do. Results: The method was tested on 88 thesis titles and journals from the computer science domain. The accuracy of the result was 94.6{\%}. These results proved the viability of this approach for distant languages. Conclusion: Based on the achieved results, we have managed to perform the syntactic reordering within an Arabic noun phrases to English translation task by using transfer-based machine translation and also achieved reasonable improvements in translation quality over related approach.",
keywords = "Arabic language processing, Machine translation, Noun phrases, Npae-Rbmt, Transfer-based approach",
author = "Omar Shirko and Nazlia Omar and Haslina Arshad and Mohammed Albared",
year = "2010",
language = "English",
volume = "6",
pages = "350--356",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "3",

}

TY - JOUR

T1 - Machine translation of noun phrases from Arabic to english using transfer-based approach

AU - Shirko, Omar

AU - Omar, Nazlia

AU - Arshad, Haslina

AU - Albared, Mohammed

PY - 2010

Y1 - 2010

N2 - Problem statement: Any Arabic to English Machine Translation (MT) system should be capable of dealing with word order which Arabic exhibits. This poses a significant challenge to MT due to the vast number of ways to express the same sentence in Arabic. The ordering features are very important and should be carefully applied to ensure the generation of sentence in the target language. Because they apply to the target language, it should fulfill the specific requirement of this language. Mistakes in the MT output can be either the result of analysis problems at the source language level, or due to generation problem at target language level. Word order rules are crucial for the generation of sentences in the target language. They also serve as rules for the ordering of sentence constituents. These rules draw their information from the syntactic knowledge. The word order problem becomes more obvious when making machine translation between languages that have rich morphological variations. Approach: The main objective of this research is to develop a machine translation that translates Arabic noun phrases into English by using transfer-based approach. A system called Npae-Rbmt has been developed in this research. Transfer-based machine translation is one instance of rulebased machine-translation approaches and is currently one of the most widely used methods of machine translation. The idea of transfer-based machine translation it is necessary to have an intermediate representation that captures the "meaning" of the original sentence in order to generate the correct translation. Using advantages of transfer-based machine translation such as analysis step, the Transfer-based becomes simpler as linguistic analysis goes deeper-as the representation of analysis step becomes more abstract. In fact, a major goal of MT research is to define a level of analysis which is so deep in which transfer-based machine translation is able to do. Results: The method was tested on 88 thesis titles and journals from the computer science domain. The accuracy of the result was 94.6%. These results proved the viability of this approach for distant languages. Conclusion: Based on the achieved results, we have managed to perform the syntactic reordering within an Arabic noun phrases to English translation task by using transfer-based machine translation and also achieved reasonable improvements in translation quality over related approach.

AB - Problem statement: Any Arabic to English Machine Translation (MT) system should be capable of dealing with word order which Arabic exhibits. This poses a significant challenge to MT due to the vast number of ways to express the same sentence in Arabic. The ordering features are very important and should be carefully applied to ensure the generation of sentence in the target language. Because they apply to the target language, it should fulfill the specific requirement of this language. Mistakes in the MT output can be either the result of analysis problems at the source language level, or due to generation problem at target language level. Word order rules are crucial for the generation of sentences in the target language. They also serve as rules for the ordering of sentence constituents. These rules draw their information from the syntactic knowledge. The word order problem becomes more obvious when making machine translation between languages that have rich morphological variations. Approach: The main objective of this research is to develop a machine translation that translates Arabic noun phrases into English by using transfer-based approach. A system called Npae-Rbmt has been developed in this research. Transfer-based machine translation is one instance of rulebased machine-translation approaches and is currently one of the most widely used methods of machine translation. The idea of transfer-based machine translation it is necessary to have an intermediate representation that captures the "meaning" of the original sentence in order to generate the correct translation. Using advantages of transfer-based machine translation such as analysis step, the Transfer-based becomes simpler as linguistic analysis goes deeper-as the representation of analysis step becomes more abstract. In fact, a major goal of MT research is to define a level of analysis which is so deep in which transfer-based machine translation is able to do. Results: The method was tested on 88 thesis titles and journals from the computer science domain. The accuracy of the result was 94.6%. These results proved the viability of this approach for distant languages. Conclusion: Based on the achieved results, we have managed to perform the syntactic reordering within an Arabic noun phrases to English translation task by using transfer-based machine translation and also achieved reasonable improvements in translation quality over related approach.

KW - Arabic language processing

KW - Machine translation

KW - Noun phrases

KW - Npae-Rbmt

KW - Transfer-based approach

UR - http://www.scopus.com/inward/record.url?scp=77952508884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952508884&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:77952508884

VL - 6

SP - 350

EP - 356

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 3

ER -