A Hybrid Rules and Statistical Method for Arabic to English Machine Translation

Abstract

Arabic is one of the six major world languages. It originated in the area currently known as the Arabian Peninsula. Arabic is the joint official language in Middle Eastern and African states. Large communities of Arabic speakers have existed outside of the Middle East since the end of the last century, particularly in the United States and Europe. So finding a quick and efficient Arabic machine translator has become an urgent necessity, due to the differences between the languages spoken in the world’s communities and the vast development that has occurred worldwide. Arabic combines many of the significant challenges of other languages like word order and ambiguity. The word ordering problem because of Arabic has four sentence structures which allow different word orders. Ambiguity in the Arabic language is a notorious problem because of the richness and complexity of Arabic morphology. The core problems in machine translation are reordering the words and estimating the right word translation among many options in the lexicon. The Rule-Based Machine translation (RBMT) approach is the way to reorder words, and the statistical approach, such as Expectation Maximisation (EM), is the way to select right word translations and count word frequencies. Combining RBMT with EM plays an impotent role in generating a good-quality MT. This paper presents a combination of the rule-based machine translation (RBMT) approach with the Expectation Maximisation (EM) algorithm. These two techniques have been applied successfully to word ordering and ambiguity problems in Arabic-to-English machine translation