Mining the whole set of person names from the Tibetan Web

摘要

Along with the rapid development of Tibetan language information and Tibetan Web in recent years, personal information becomes a main focus of researchers. While, due to the complexity of the Web information, the extraction of person names is difficult, especially in Tibetan Web. This paper presents a rule-based approach, which is based on the case-auxiliary words and lexicon, to extract the person name from the Tibetan Web. According to the grammar information and statistical rules, we have developed a person name extraction system, which is used for the Tibetan Web. We design a series of experiments to evaluate the performance of the system, and the evaluation results are satisfactory.