【24h】

A QA document retrieval method based on phrase-level analysis of the input natural language query

机译:基于输入自然语言查询短语层次分析的QA文档检索方法

获取原文
获取原文并翻译 | 示例
           

摘要

In the field of help-desk business, the need for an accurate QA document retrieval system is intensively increasing. Many QA document retrieval systems have been realized by simply applying conventional full-text search engines designed for general search purposes. But the output of those systems contains not a few "noise" documents less concerned with the content of input query, because they merely treat input query sentences as a set of keywords for search and don't consider with the intentional aspects or semantic content of the sentences. To reduce this noise-jamming problem, we are now developing a new search method that uses phrase-level semantic constraints derived from the input query to select relevant documents to the query. In this paper; we described the search method and the experimental system based on it.
机译:在服务台业务领域,对准确的质量检查文档检索系统的需求正日益增加。通过简单地应用为一般搜索目的而设计的常规全文搜索引擎,已经实现了许多QA文档检索系统。但是这些系统的输出中包含了一些与输入查询的内容无关的“噪音”文档,因为它们只是将输入查询语句视为一组搜索关键词,而没有考虑输入关键词的故意方面或语义内容。句子。为了减少这种干扰噪音的问题,我们现在正在开发一种新的搜索方法,该方法使用从输入查询派生的短语级语义约束来选择查询的相关文档。本文我们描述了搜索方法和基于它的实验系统。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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