首页> 外国专利> NEW WORD CANDIDATE EXTRACTION DEVICE, NEW WORD CANDIDATE EXTRACTION METHOD, AND PROGRAM

NEW WORD CANDIDATE EXTRACTION DEVICE, NEW WORD CANDIDATE EXTRACTION METHOD, AND PROGRAM

机译:新单词候选词抽取设备,新单词候选词抽取方法和程序

摘要

The present invention makes it possible to accurately extract a high priority candidate word that is to be registered in a dictionary. An input unit 110 receives input of a registration candidate word, which is a notation of a word, and a reading of the registration candidate word. If a registration candidate determination unit 130 determines that the reading of the registration candidate word does not match a registration candidate word reading obtained by morpheme analysis performed on the registration candidate word by a morpheme analysis unit 120, a generic word determination unit 150 calculates the appearance frequency of the registration candidate word with respect to a text group, and if the appearance frequency is at least a threshold value, determines the registration candidate word to be a new word candidate that is to be registered in a dictionary.
机译:本发明使得可以准确地提取要在字典中注册的高优先级候选词。输入单元110接收作为词的符号的注册候选词的输入以及注册候选词的读取。如果注册候选确定单元130确定注册候选词的读取与通过词素分析单元120对注册候选词进行的词素分析获得的注册候选词读取不匹配,则通用词确定单元150计算外观登记候选词相对于文本组的频率,并且如果出现频率至少是阈值,则将登记候选词确定为要登记在词典中的新词候选。

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