Tip destekli çeviri kalıpları ile örnek tabanlı otomatik çeviri

Example based machine translation is a translation technique that leans onmachine learning paradigm. This technique had been modeled by the learningprocess as: a man is given short and simple sentences in language A with theircorrespondences in language B; he memorizes these pairs and then becomes ableto translate new sentences via these pairs in the memory. In our system thetranslation pairs are kept as translation templates. A translation template isinduced from given two translation examples by replacing differing parts in theseexamples by variables. A variable replacing a difference that consists of twodiffering parts (one from the first example, and the other one from the secondexample) is a generalization of those two differing parts and these variables aresupported with part-of-speech tag information in order to deteriorate incorrecttranslations. After the learning phase, translation is achieved by finding theappropriate template(s) and replacing the variables.Keywords: Example Based Machine Translation, Type Associated TranslationTemplate Induction, Machine Learning.iii