M.Sc. Tezi Görüntüleme | |||||||||||||||||||||
|
|
||||||||||||||||||||
Summary: This paper describes the details of a machine translation system for Turkish-Turkmen chat. The machine translation system is developed to provide a web based chat medium for Turkish and Turkmen speaking people. Turkish and Turkmen languages are closely related but they have rather complex morphotactics. Machine translation between closely related languages is easier than translation between languages that are not closely related. Thus, less effort needed to develop a translation system between closely related languages because many parts of related languages such as grammars and vocabularies are common. Hence, syntactic and semantic analysis may not be necessary since the translation system makes morphological analysis most of the time. So, simple translation rules and context dependent bilingual dictionaries may be sufficient for the translation. Turkish and Turkmen are agglutinative languages with respect to word structures formed by productive affixations of derivational and inflectional suffixes to root words. Therefore, different words can be constructed from roots and morphemes to describe objects and concepts. Basically, the translation system takes a Turkish or Turkmen sentence and analyses all the words morphologically. Then, it translates the root words and morphemes, and finally generates the Turkish or Turkmen sentence morphologically. Most of the time the input sentence is translated to at least one or more true output sentence. Finally, a context dependent decision mechanism is employed to determine the true output sentences.Key Words: Natural Language Processing, Machine Translation, Agglutinative Languages, Turkish, Turkmen, Chat System. |