首页> 外文会议>Active media technology >Chinese Question Retrieval System Using Dependency Information
【24h】

Chinese Question Retrieval System Using Dependency Information

机译:依赖信息的中文问题检索系统

获取原文
获取原文并翻译 | 示例

摘要

Discussion boards and online forums provide a platform for users to share ideas, discuss issues and communicate with each other. Nowadays most of the discussion boards are used as problem-solving platforms which can be seen as question-answering knowledge bases. Therefore, if system can automatically locate the similar questions which have appeared previously, then the same answers could be returned to users to eliminate the time users wait for. In this paper, a novel question retrieval method is proposed. Keywords based inverted index is chosen as the basis technology, and dependency information, language model, and simple semantic information is used to extend it. Experimental results show the effectiveness and benefits of our approach.
机译:讨论区和在线论坛为用户提供了一个共享想法,讨论问题以及相互交流的平台。如今,大多数讨论板都用作解决问题的平台,可以看作是回答问题的知识库。因此,如果系统可以自动定位先前出现的类似问题,则可以将相同的答案返回给用户,从而消除了用户等待的时间。本文提出了一种新颖的问题检索方法。选择基于关键词的倒排索引作为基础技术,并使用依赖信息,语言模型和简单语义信息对其进行扩展。实验结果表明了我们方法的有效性和益处。

著录项

  • 来源
    《Active media technology》|2010年|p.288-295|共8页
  • 会议地点 Toronto(CA);Toronto(CA)
  • 作者单位

    Department of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China;

    Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, 100081, China;

    Division of Student Affairs, Hebei University of Science and Technology, Shijiazhuang 050018, China;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 多媒体技术与多媒体计算机;
  • 关键词

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