It has been proved that large-scale realistic Knowledge Based Machine Translation (KBMT) applications require acquisition of huge knowledge about language and about the world. This knowledge is encoded in computational grammars, lexicons and domain models. Another approach – which avoids the need for collecting and analyzing massive knowledge- is the Example Based approach, which is the topic of this paper.

We show through the paper that using Example Based in its native form is not suitable for translating into Arabic. Therefore a modification to the basic approach is presented to improve the accuracy of the translation process. The basic idea of the new approach is to extract, from a parallel Bilingual Corpus, all possible templates that could match part of the source sentence. These templates are selected as suitable candidate chunks for the source sentence. The corresponding Arabic templates are also extracted and represented in a tree structure. Each tree branch represents one possible string of templates candidate to represent the target sentence. The shortest path or the most probable tree branch is selected to represent the target sentence. Finally the Arabic translation of the selected tree branch is generated.