Using Semantic Knowledge in the Uyghur-Chinese Person Name Transliteration

Abstract

In this paper, we propose a transliteration approach based on semantic information (i.e., language origin and gender) which are automatically learnt from the person name, aiming to transliterate the person name of Uyghur into Chinese. The proposed approach integrates semantic scores (i.e., performance on language origin and gender detection) with general transliteration model and generates the semantic knowledge-based model which can produce the best candidate transliteration results. In the experiment, we use the datasets which contain the person names of different language origins: Uyghur and Chinese. The results show that the proposed semantic transliteration model substantially outperforms the general transliteration model and greatly improves the mean reciprocal rank (MRR) performance on two datasets, as well as aids in developing more efficient transliteration for named entities.

Novel Approaches for Applying Linguistic Processing Techniques Based on Pattern Recognition and Machine Learning

“…Murat et al [14] propose a transliteration approach based on semantic information, such as language origin and gender, which are automatically learned by person name from Uyghur to Chinese. The proposed approach integrates semantic scores with a general transliteration model and generates the semantic knowledge-based model, which can produce the best candidate transliteration results.…”