首页> 外国专利> Method for restoring Korean omitted components based on language model

Method for restoring Korean omitted components based on language model

机译:基于语言模型的韩文遗漏成分恢复方法

摘要

The present invention relates to a method for restoring a Korean omitted component based on a language model, comprising: an input step of receiving a sentence; An analysis step of analyzing the syntax of the input sentence; A determining step of determining whether there is an omitted word through syntax analysis; An extraction step of extracting a restoration candidate word from within the sentence by targeting a phrase of a sentence in which there is no omitted word among previous phrases if there is a word omitted in the determination step; A language model application step of generating configurable restoration candidate sentences using components in which the omitted component exists; And a step of determining an omission target of calculating a construction probability value for each generated restoration candidate sentence, and selecting a restoration candidate sentence using the calculated construction probability value.
机译:本发明涉及一种基于语言模型的韩语省略成分的恢复方法,包括:接收句子的输入步骤;分析输入句子的语法的分析步骤;通过语法分析确定是否存在遗漏词的确定步骤;如果确定步骤中有遗漏的单词,则通过以先前短语中没有遗漏单词的句子的短语为目标,从句子中提取恢复候选单词的提取步骤;语言模型应用步骤,使用存在省略的组件的组件生成可配置的恢复候选语句;以及确定省略目标的步骤,该目标针对每个生成的恢复候选句子计算构建概率值,并使用计算出的构建概率值选择恢复候选句子。

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