Transliteration from Arabic to English

Machine translation has been an active field in Natural Language Processing. Although the quality of translation cannot reach that of a human, it is getting closer. One of the major sub-tasks in this field is ‘transliteration’, which is mapping the letters from the source language to the letters of target language. It would be useful for translating the proper names, location names and any out-of-vocabulary word found in the source text. The abundance of names and the lack of a comprehensive bilingual dictionary compel us to find methods to automatically transliterate the names in the given text and not rely on lookup tables. This research mainly focuses on the task of transliteration and by using statistical and dictionary approaches tries to obtain the best transliterations. The language pair under study is Arabic and English.

Mehdi Kashani
Faculty Supervisor: 
Dr. Fred Popowich
British Columbia