Machine transliteration of names in Arabic text

Abstract

We present a transliteration algorithm based on sound and spelling mappings using finite state machines. The transliteration models can be trained on relatively small lists of names. We introduce a new spelling-based model that is much more accurate than state-of-the-art phonetic-based models and can be trained on easier-to-obtain training data. We apply our transliteration algorithm to the transliteration of names from Arabic into English. We report on the accuracy of our algorithm based on exact-matching criterion and based on human-subjective evaluation. We also compare the accuracy of our system to the accuracy of human translators.