Arabic machine transliteration using an attention-based
encoder-decoder model

Hadj Ameur, MS; Meziane, F; Guessoum, A

Abstract

Transliteration is the process of converting words from a given source language alphabet to a target language alphabet, in a way
that best preserves the phonetic and orthographic aspects of the transliterated words. Even though an important effort has been
made towards improving this process for many languages such as English, French and Chinese, little research work has been
accomplished with regard to the Arabic language. In this work, an attention-based encoder-decoder system is proposed for the
task of Machine Transliteration between the Arabic and English languages. Our experiments proved the efficiency of our proposal
approach in comparison to some previous research developed in this area.

Citation

encoder-decoder model. Procedia Computer Science, 117, 287-297. https://doi.org/10.1016/j.procs.2017.10.120

• Journal Article Type: Article
• Conference Name: 3rd International Conference on Arabic Computational Linguistics (ACLing 2017)
• Conference Location: Dubai, UAE
• Start Date: Nov 5, 2017
• End Date: Nov 6, 2017
• Acceptance Date: Sep 6, 2017
• Online Publication Date: Nov 9, 2017
• Publication Date: Nov 9, 2017
• Deposit Date: Sep 13, 2017
• Publicly Available Date: Dec 1, 2017
• Journal: Procedia Computer Science
• Print ISSN: 1877-0509
• Publisher: Elsevier
• Volume: 117
• Pages: 287-297
• DOI: https://doi.org/10.1016/j.procs.2017.10.120
• Publisher URL: http://dx.doi.org/10.1016/j.procs.2017.10.120
• Related Public URLs: http://acling2017.org/
• Additional Information: Additional Information : This paper was submitted to ACLing 2017, the 3rd International Conference on Arabic Computational Linguistics - see organisation link below.; Event Type : Conference