A Hybrid Approach Using Maximum Entropy Model and Rules to Identify Tibetan Person Names

Tibetan person name recognition is one of the most difficult tasks in the area of Tibetan information processing, and the effect of recognition impacts directly on the precision of Tibetan word segmentation and the performance of relative application systems, which include Tibetan-Chinese machine translation, Tibetan information search, text categorization, etc. Based on the analysis of wording rules and features of Tibetan name, this paper proposed a method which combines maximum entropy and rules to identify Tibetan person names. The experiment shows that this approach works really well for the value of F1-measure reaches 95.92%.