首页> 外文期刊>Information Processing & Management >High-performance FAQ retrieval using an automatic clustering method of query logs
【24h】

High-performance FAQ retrieval using an automatic clustering method of query logs

机译:使用查询日志的自动聚类方法进行高性能FAQ检索

获取原文
获取原文并翻译 | 示例
           

摘要

To resolve some of lexical disagreement problems between queries and FAQs, we propose a reliable FAQ retrieval system using query log clustering. On indexing time, the proposed system clusters the logs of users' queries into predefined FAQ categories. To increase the precision and the recall rate of clustering, the proposed system adopts a new similarity measure using a machine readable dictionary. On searching time, the proposed system calculates the similarities between users' queries and each cluster in order to smooth FAQs. By virtue of the cluster-based retrieval technique, the proposed system could partially bridge lexical chasms between queries and FAQs. In addition, the proposed system outperforms the traditional information retrieval systems in FAQ retrieval.
机译:为了解决查询和FAQ之间的一些词汇不一致问题,我们提出了一种使用查询日志聚类的可靠FAQ检索系统。在建立索引时,建议的系统将用户查询的日志聚集到预定义的FAQ类别中。为了提高聚类的精度和召回率,提出的系统采用了一种新的使用机器可读字典的相似性度量。在搜索时间上,所提出的系统计算用户查询与每个群集之间的相似度,以简化常见问题解答。借助于基于集群的检索技术,所提出的系统可以部分桥接查询和FAQ之间的词汇鸿沟。此外,该系统在FAQ检索中优于传统的信息检索系统。

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