改进的基于义原同现频率的汉语词义排歧方法

针对传统的基于义原同现频率的汉语词义排歧方法存在“盲目性”的不足，本文根据《知网》中对概念定义的描述，分别计算多义词的每个义项与特征词的第一独立义原、其他独立义原、关系义原、符号义原之间的相关系数；最后通过比较多义词的每个义项与特征词之间的相关系数来决定多义词的义项。经过实验验证，该方法进一步提高了词义排歧的效果。

An Improved Chinese Word Sense Disambiguation Method Based on Primitive Co-Occurrence Data

The fault of blindness exists in traditional Chinese word sense disambiguation methods which are based on primitive co-occurrence data. Based on the depiction for the concept of Hownet,the authors calculate these relation- moduluses between the first unattached primitive,the other unattached primitive,the relation primitive,the sign primitive of each sense of a multivocal word and that of character-words.Finally, the sense of the multivocal word is chosen by comparing these relation- moduluses between each sense of the multivocal word and character-words. The experimental results show that the accuracy of word sense disambiguation of the method is higher.