首页> 外国专利> Apparatus and method for computing noun similarities using semantic contexts

Apparatus and method for computing noun similarities using semantic contexts

机译:使用语义上下文计算名词相似度的设备和方法

摘要

A semantic-based noun similarity calculation method according to the present invention comprises: checking a feature vector map for a plurality of adjectives included in each of a plurality of noun phrases extracted from a sentence and a document; generating a plurality of first feature vector sets on the basis of a plurality of nouns included in the each of the plurality of noun phrases; generating a plurality of second feature vector sets based on the feature vector map checking the generated plurality of first feature vector sets; calculating an adjective similarity by using two second feature vector sets for each of two nouns based on the second feature vector sets; and calculating a semantic similarity for the two nouns based on the adjective similarity.
机译:根据本发明的基于语义的名词相似度计算方法包括:检查特征向量图以查找从句子和文档中提取的多个名词短语的每一个中包括的多个形容词;基于多个名词短语的每一个中包括的多个名词,生成多个第一特征向量集;基于特征向量图生成多个第二特征向量集,并检查生成的多个第一特征向量集;通过基于第二特征向量集为两个名词中的每一个使用两个第二特征向量集来计算形容词相似度;并根据形容词相似度计算两个名词的语义相似度。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号