摘要
总结了维吾尔地名结构及其特点,并结合维吾尔地名内部结构特征,手动建立了基于新疆维吾尔自治区的地名词典库、首词库、中间词库和特征词库,研究了基于规则的维吾尔语地名识别方法和技术。以包含地名的较大规模维吾尔文本作为测试样本,利用地名内部结构和相邻词信息,通过匹配算法进行了地名识别,并用Visual C++编程工具实现了维吾尔语地名识别算法。最后,给出了实验结果,并分析了出错原因及相应的对策。
A research on the rule-based method for recognizing place names in text is conducted, and based on the internal structure feature of Uyghur place names, Xinjiang place name dictionary, first-word dictionary, middle-word dictionary and special word dictionary are established. Meanwhile, with large-scale text containing place names as the testing sample, and by using internal structure of place names and adjacent word information, the place name recognition could be realized through matching algorithm. And with is achieved. Finally, an analysis is done on the reference for the further research. Visual C＋＋, the place name recognition system experiment result, and this could serve as a
出处
《通信技术》
2013年第7期103-105,共3页
Communications Technology
基金
国家自然科学基金资助项目(批准号:61163033)
国家科技支撑计划(No.2009BAH41B03)
教育部新世纪优秀人才支持计划资助项目(No.NCET-10-0969)
关键词
维吾尔语
地名识别
地名词典
命名实体识别
Uyghur
place name recognition
place name dictionary＇ named entity recognition
