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