Naxi-English bilingual word alignment based on language feature model of Naxi

To achieve the corpus of Naxi - English bilingual words alignment, aim at syntactic characteristics of Naxi language. A Naxi-English bilingual words alignment method is proposed. This method uses the log-linear model, and introduces feature functions based on the characteristic of the Naxi language, which are English - Naxi interval switching function and Naxi - English bilingual words position transformation function. With the artificial labeling of Naxi - English words alignment corpus, the parameters of the model are trained by using the minimum error. The Naxi-English bilingual words are alignment automatically by this model. Experiments with IBM Model 3 as a benchmark, and gradually add constraints on the characteristics of the Naxi language with the basis of IBM Model 3. The final experiment results show that the Naxi - English bilingual word alignment accuracy can be improved significantly with the feature functions which are base on characteristic of Naxi.