分类词典编撰的域词语聚类实现.docVIP

分类词典编撰的领域词语聚类实现 刘华 中文提要：针对分类词典中学科词条的获取和选择问题，我们利用文本分类和聚类中特征提取的方法进行词语聚类，从而达到辅助词典编撰的目的。 关键词：分类词典 文本分类 特征提取 词语聚类 Studies on Words Clustering in lexicography Liu Hua1，2 Zhou LingYan1 Zhang Pu2 1（College of Chinese Language and Culture of Jinan University，Guangzhou，510000） 2（Beijing Language University，Beijing，100000） E-mail:liuhua0461@ Abstract: For obtaining and selecting subject lemma auxiliary to building classified dictionary, this paper presents an algorithm that clusters field Words in large-scale classed corpus by character extraction in text classing. Key words: Lexicography, Text Classi