English to Arabic Example-based Machine Translation System


Abstract –The Example Based Machine Translation (EBMT) system retrievessimilar examples (pairs of source phrases, sentences, or texts and their translations) froma database of examples, adapting the examples to translate new input. The Example Base(EB) is an important component in an EBMT system. It handles the storage to support thetranslation process. Thus, an efficient EB must be capable of handling a massive volumeof examples at an adequately high speed.In this research, a new approach to reduce the redundancy problem that some EBMTsystems suffer from is suggested by designing EB using B+ tree. The EB is used to storethe examples of a particular field in a manner that reduces the redundancy of theseexamples (or even sub examples) in order to provide efficient memory usage and tominimize the search time. The lexicon of the proposed method is represented by usingtwo databases. One database is used for storing the English words and another database isused for storing the English transfer grammars.


EBMT, EB, B+ Tree.