A Hybrid Approach for Converting Written Egyptian Colloquial Dialect into Diacritized Arabic
Hitham Abo-Bakr, Khaled F. Shaalan, Ibrahim Ziedan · International Conference on Informatics and Systems · 2008
Recently the rate of written colloquial text has increased dramatically. It is being used as a medium of expressing ideas especially across the WWW, usually in the form of blogs and partially colloquial articles. Most of these written colloquial has been in the Egyptian colloquial dialect, which is considered the most widely dialect understood and used throughout the Arab world. Modern Standard Arabic is the official Arabic language taught and understood all over the Arab world. Diacritics play a key role in disambiguating Arabic text. The reader is expected to infer or predict vowels from the context of the sentence. Inferring the full form of the Arabic word is also useful when developing Arabic natural language processing tools and applications. In this paper, we introduce a generic method for converting a written Egyptian colloquial sentence into its corresponding diacritized Modern Standard Arabic sentence which could easily be extended to be applied to other dialects of Arabic. In spite of the non-availability of linguistic Arabic resources for this task, we have developed techniques for lexical acquisition of colloquial words which are used for transferring written Egyptian Arabic into Modern Standard Arabic. We successfully used Support Vector Machine approach for the diacritization (aka vocalization or vowelling) of Arabic text.