Development of a Translation Memory System for Turkish to English

DEVELOPMENT OF A TRANSLATION MEMORY SYSTEM FOR TURKISH TO ENGLISH This thesis studies on translation memory systems and development of a translation memory system on Turkish to English. A translation memory system is a tool that is designed for helping human translators during translation. It uses a database that consists of text parts such as blocks, paragraphs, sentences, or phrases in one language that is called source language and their translations in another language which is called target language. The translation memory system searches its database to find the closest sentence for the source sentence that has to be translated. Translation memory systems that are used by human translators offer the best matches for the review of the translator. The translator either accepts the result or rejects it, or makes some modifications, or asks for the second best result. This thesis presents a translation memory system based on both orthographic and semantic knowledge. Translation memory system concept is not popular for Turkish. To the best of our knowledge, there is not a translation memory system developed for Turkish to English. This is the first translation memory system on Turkish to English. The proposed system uses a sentence level memory but exploits words and various linguistic features of the language. The similarity search algorithm takes advantage of highly agglutinative word structures, inflectional and derivational affixes of Turkish. The presented framework considers orthographic, morphologic, lexical, semantic and syntactical features. It gathers good success rate on Turkish (about 0.40 BLEU score) and is expected to be helpful on the translation of languages that have similar linguistic structure with Turkish.