首页> 外国专利> COMPOUND WORD GENERATION DEVICE, COMPOUND WORD GENERATION METHOD AND COMPOUND WORD GENERATION PROGRAM

COMPOUND WORD GENERATION DEVICE, COMPOUND WORD GENERATION METHOD AND COMPOUND WORD GENERATION PROGRAM

机译:复合词生成装置,复合词生成方法和复合词生成程序

摘要

PROBLEM TO BE SOLVED: To provide a compound word generation device and a compound word generation method which can generate compound words without using learning texts.SOLUTION: A text division unit 101 divides an input text into a plurality of character strings based on space characters, and a character string occurrence number counting unit 102 counts the number of occurrence of each character string divided by the text division unit 101 and also creates a set of character string including divided character strings as candidate character strings. Then, based on the candidate character strings included in the set of character strings created by the character string occurrence number counting unit 102, from the set of character strings, an element character string combination extraction unit 103 extracts combinations of element character strings that can compose the candidate character strings by connecting a plurality of element character strings which are compound word elements.
机译:解决的问题:提供一种无需使用学习文本即可生成复合词的复合词生成装置和复合词生成方法。解决方案:文本划分单元101基于空格字符将输入文本划分为多个字符串,字符串出现次数计数单元102对由文本划分单元101划分的每个字符串的出现次数进行计数,并且还创建包括被划分的字符串作为候选字符串的一组字符串。然后,元素字符串组合提取单元103基于由字符串出现次数计数单元102创建的字符串集合中包括的候选字符串,从该字符串集合中提取可以构成的元素字符串的组合。通过连接作为复合词元素的多个元素字符串来候选字符串。

著录项

  • 公开/公告号JP2012159875A

    专利类型

  • 公开/公告日2012-08-23

    原文格式PDF

  • 申请/专利权人 NTT DOCOMO INC;

    申请/专利号JP20110017094

  • 发明设计人 TSUJINO KOSUKE;

    申请日2011-01-28

  • 分类号G06F17/30;G06F17/22;

  • 国家 JP

  • 入库时间 2022-08-21 17:44:21

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