Uyghur-Chinese Translation Disambiguation Method Research Based on Knowledge Automatic-Acquisition

ABSTRACT

This thesis studies the disambiguation method in Uyghur-Chinese translation, and proposes the design philosophy of automatic-acquisition in translation label library aiming at the deficiency of disambiguation corpus in Uyghur. It refers to the existing Uyghur-Chinese bilingual dictionary, Chinese corpus and the Internet, and acquires the corresponding Chinese translation label examples to Uyghur automatically. On this basis, this thesis designs a Uyghur-Chinese disambiguation model, and refines the meaning probability definition based on HMM model. It increases the model’s backwards-dependence, and the model’s ability to obtain contextual information. To use the model to learn disambiguation knowledge from translation label corpus can eliminate the ambiguity in new Uyghur ambiguous words. From the experiment result, it can prove that the Uyghur-Chinese translation disambiguation framework based on automatically acquired corpus is effective, and increases with the increasing of the scale of translation label corpus, degree of accuracy of the disambiguation result also increases accordingly.

Keywords: