Machine translation (MT) is an essential component of many multilingual applications. Existence of out-of-vocabulary (OOV) words annoys MT systems. Despite of the amount of data available for training, many OOV words do not appear in the source dictionary, and this is a common problem in MT systems. OOV words are mostly named entities such as people, company and place names, technical terms and foreign words that have not appeared in the dictionaries. Transcribing the source languages and using it directly in the target language, is a solution for OOV words. This process of transcription is known as transliteration.