最大熵与转换规则相结合识别中文名词短语  

Maximum Entropy and Transformation Rules Combined Identification Chinese Noun Phrase

作　　者：卢朝华 蒙皓兵 

机构地区：[1]商丘科技职业学院,河南商丘476000

出　　处：《计算机光盘软件与应用》2011年第3期1-2,共2页Computer CD Software and Application

基　　金：教育部科学技术重点资助项目

摘　　要：本文针对统计方法和规则方法各自的特点，提出基于最大熵方法和转换规则方法相结合的中文基本名词短语识别算法，该算法是在一定词性标注的基础上实现的。在训练和测试两个阶段中，均先采用最大熵方法识别基本名词短语，然后将已具有一定精度的识别结果作为初始标注结果运用于转换规则方法中。实验表明，该方法具有一定的可行性。Utilizing features of the statistic approach and the regulation approach,an Chinese noun phrase identification algorithm based on combing maximum entropy approach with transformation-rules approach is presented.The algorithm is based on certain POS（parts of speech）tagger.During the training phase and the application phase, maximum entropy approach is first applied to the initialization process of transformation-rules approach,and the transformation-rules approach is then run on its results already having certainly accuracy.Experimental showed that this combined algorithm has feasibility.

关 键 词：基本名词短语 短语识别 最大熵 转换规则 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]