Grammar-based and example-based techniques in machine translation from English to Arabic

Mouiad Fadiel Alawneh, Tengku Mohd Sembok, Masnizah Mohd

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In the modern world, there is an increased need for language translation. This paper presents English to Arabic approach for translating well-structured English sentences into well-structured Arabic sentences, using a grammar-based and example-translation techniques to handle the problems of ordering and agreement. This technique combines rule-based MT (RBMT) and example-based MT (EBMT) which is called hybrid-based MT (HERBMT). The proposed methodology is flexible and scalable. The main advantages of HERBMT are that it combines the advantages of RBMT and EBMT, and it can be applied to other languages with minor modifications. EBMT extracts an example of target language sentences that are analogous to input source language sentences. The extraction of appropriate translated sentences is preceded by an analysis stage for the decomposition of input sentences into appropriate fragments. RBMT is used when examples of the source language to be translated into the target language are not found in the machine database. The OAK Parser is used to analyze the input English text to get the part of speech (POS) for each word in the text as a pre-translation process. A major design goal of this system is that it will be used as a stand-alone tool, and can be integrated with a general machine translation system for English sentences. The evaluation is carried out on 250 independent test suites, and the analysis indicates that HERBMT achieved good performance with an average of 97.2% precision.

Original languageEnglish
Title of host publication2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013
DOIs
Publication statusPublished - 2013
Event2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013 - Rabat
Duration: 26 Mar 201327 Mar 2013

Other

Other2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013
CityRabat
Period26/3/1327/3/13

Fingerprint

grammar
language
Decomposition
methodology
evaluation
performance

Keywords

  • Agreement
  • Example-based
  • Hybrid-based
  • MT
  • OAK Parser
  • Rule-Based
  • Word reorder

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Communication

Cite this

Alawneh, M. F., Sembok, T. M., & Mohd, M. (2013). Grammar-based and example-based techniques in machine translation from English to Arabic. In 2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013 [6518910] https://doi.org/10.1109/ICT4M.2013.6518910

Grammar-based and example-based techniques in machine translation from English to Arabic. / Alawneh, Mouiad Fadiel; Sembok, Tengku Mohd; Mohd, Masnizah.

2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013. 2013. 6518910.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alawneh, MF, Sembok, TM & Mohd, M 2013, Grammar-based and example-based techniques in machine translation from English to Arabic. in 2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013., 6518910, 2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013, Rabat, 26/3/13. https://doi.org/10.1109/ICT4M.2013.6518910
Alawneh MF, Sembok TM, Mohd M. Grammar-based and example-based techniques in machine translation from English to Arabic. In 2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013. 2013. 6518910 https://doi.org/10.1109/ICT4M.2013.6518910
Alawneh, Mouiad Fadiel ; Sembok, Tengku Mohd ; Mohd, Masnizah. / Grammar-based and example-based techniques in machine translation from English to Arabic. 2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013. 2013.
@inproceedings{f766b446b01a4c63b846cafacfca4242,
title = "Grammar-based and example-based techniques in machine translation from English to Arabic",
abstract = "In the modern world, there is an increased need for language translation. This paper presents English to Arabic approach for translating well-structured English sentences into well-structured Arabic sentences, using a grammar-based and example-translation techniques to handle the problems of ordering and agreement. This technique combines rule-based MT (RBMT) and example-based MT (EBMT) which is called hybrid-based MT (HERBMT). The proposed methodology is flexible and scalable. The main advantages of HERBMT are that it combines the advantages of RBMT and EBMT, and it can be applied to other languages with minor modifications. EBMT extracts an example of target language sentences that are analogous to input source language sentences. The extraction of appropriate translated sentences is preceded by an analysis stage for the decomposition of input sentences into appropriate fragments. RBMT is used when examples of the source language to be translated into the target language are not found in the machine database. The OAK Parser is used to analyze the input English text to get the part of speech (POS) for each word in the text as a pre-translation process. A major design goal of this system is that it will be used as a stand-alone tool, and can be integrated with a general machine translation system for English sentences. The evaluation is carried out on 250 independent test suites, and the analysis indicates that HERBMT achieved good performance with an average of 97.2{\%} precision.",
keywords = "Agreement, Example-based, Hybrid-based, MT, OAK Parser, Rule-Based, Word reorder",
author = "Alawneh, {Mouiad Fadiel} and Sembok, {Tengku Mohd} and Masnizah Mohd",
year = "2013",
doi = "10.1109/ICT4M.2013.6518910",
language = "English",
isbn = "9781479901340",
booktitle = "2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013",

}

TY - GEN

T1 - Grammar-based and example-based techniques in machine translation from English to Arabic

AU - Alawneh, Mouiad Fadiel

AU - Sembok, Tengku Mohd

AU - Mohd, Masnizah

PY - 2013

Y1 - 2013

N2 - In the modern world, there is an increased need for language translation. This paper presents English to Arabic approach for translating well-structured English sentences into well-structured Arabic sentences, using a grammar-based and example-translation techniques to handle the problems of ordering and agreement. This technique combines rule-based MT (RBMT) and example-based MT (EBMT) which is called hybrid-based MT (HERBMT). The proposed methodology is flexible and scalable. The main advantages of HERBMT are that it combines the advantages of RBMT and EBMT, and it can be applied to other languages with minor modifications. EBMT extracts an example of target language sentences that are analogous to input source language sentences. The extraction of appropriate translated sentences is preceded by an analysis stage for the decomposition of input sentences into appropriate fragments. RBMT is used when examples of the source language to be translated into the target language are not found in the machine database. The OAK Parser is used to analyze the input English text to get the part of speech (POS) for each word in the text as a pre-translation process. A major design goal of this system is that it will be used as a stand-alone tool, and can be integrated with a general machine translation system for English sentences. The evaluation is carried out on 250 independent test suites, and the analysis indicates that HERBMT achieved good performance with an average of 97.2% precision.

AB - In the modern world, there is an increased need for language translation. This paper presents English to Arabic approach for translating well-structured English sentences into well-structured Arabic sentences, using a grammar-based and example-translation techniques to handle the problems of ordering and agreement. This technique combines rule-based MT (RBMT) and example-based MT (EBMT) which is called hybrid-based MT (HERBMT). The proposed methodology is flexible and scalable. The main advantages of HERBMT are that it combines the advantages of RBMT and EBMT, and it can be applied to other languages with minor modifications. EBMT extracts an example of target language sentences that are analogous to input source language sentences. The extraction of appropriate translated sentences is preceded by an analysis stage for the decomposition of input sentences into appropriate fragments. RBMT is used when examples of the source language to be translated into the target language are not found in the machine database. The OAK Parser is used to analyze the input English text to get the part of speech (POS) for each word in the text as a pre-translation process. A major design goal of this system is that it will be used as a stand-alone tool, and can be integrated with a general machine translation system for English sentences. The evaluation is carried out on 250 independent test suites, and the analysis indicates that HERBMT achieved good performance with an average of 97.2% precision.

KW - Agreement

KW - Example-based

KW - Hybrid-based

KW - MT

KW - OAK Parser

KW - Rule-Based

KW - Word reorder

UR - http://www.scopus.com/inward/record.url?scp=84879038804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879038804&partnerID=8YFLogxK

U2 - 10.1109/ICT4M.2013.6518910

DO - 10.1109/ICT4M.2013.6518910

M3 - Conference contribution

AN - SCOPUS:84879038804

SN - 9781479901340

BT - 2013 5th International Conference on Information and Communication Technology for the Muslim World, ICT4M 2013

ER -