首页> 外国专利> DEEP LEARNING TYPE CLASSIFICATION METHOD WITH FEATURE-BASED WEIGHTING

DEEP LEARNING TYPE CLASSIFICATION METHOD WITH FEATURE-BASED WEIGHTING

机译:基于特征加权的深度学习类型分类方法

摘要

A method for classifying a type of entity according to an exemplary embodiment includes: calculating a weight based on a qualification of a word from a context word; Converting the context word into a weight value by calculating a weight of the context word based on the qualities of the word; Combining the weight value of the context word with a vector of each word to calculate a weight reflection vector; And classifying the weight reflection vector calculated from the context word into an entity type based on the learned neural network.;
机译:根据示例性实施例的用于对实体的类型进行分类的方法包括:基于来自上下文词的词的资格来计算权重;通过根据单词的质量计算上下文单词的权重,将上下文单词转换为权重值;将上下文词的权重值与每个词的向量相结合以计算权重反射向量;然后根据学习到的神经网络,将上下文词计算得到的权重反射向量分类为实体类型。

著录项

  • 公开/公告号KR101837262B1

    专利类型

  • 公开/公告日2018-04-20

    原文格式PDF

  • 申请/专利权人 한국과학기술원;

    申请/专利号KR20160017364

  • 发明设计人 김부근;강준영;맹성현;

    申请日2016-02-15

  • 分类号G06N3/08;G06F17/27;

  • 国家 KR

  • 入库时间 2022-08-21 12:38:13

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