A Context-Aware Automatic Chinese Transliterated Person Names Recognition Approach

Chinese Transliterated Person Name (TP-Name) recognition is a special challenging task in Chinese unknown word recognition and Chinese word segmentation. Most of existing researches mainly focus on recognizing the names of Chinese person while seldom specialize in recognizing transliterated person names. In this paper, we proposed a hybrid method for TP-Name recognition based on both the context of person names exiting in and the reliability model. Besides, partial frequency statistics and proliferation option are also used to correct the misrecognized names and unrecognized names. Experiments based on a true dataset show that our approach is efficient in recognizing the TP-Names from Chinese texts. The precision rate, recall rate and F-measure are 93.81%, 98.14%, 95.92% respectively.