• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2013 IEEE International Conference in MOOC, Innovation and Technology in Education >Improving Retrieval performance of English-Hindi based Cross-Language Information Retrieval
【24h】

Improving Retrieval performance of English-Hindi based Cross-Language Information Retrieval

机译：改进基于英语-印地语的跨语言信息检索的检索性能

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The hurdle problem in Cross Language Information Retrieval (CLIR) is the poor performance when compared to monolingual performance in terms of average precision. The main reasons behind the poor performance of CLIR are query term mismatching, multiple representations of query terms and un-translated query terms. In this paper, we are putting our effort to solve the given problem which is discussed in detail. The limitations are needed to be addressed in order to increase the performance of the CLIR system. By analyzing those methods the architecture for English-Hindi CLIR system is proposed. Pre and post query expansion is used to improve the performance of English-Hindi CLIR system using English and Hindi WordNet, Local Expansion using initial query, definition based pre query expansion and keyword ranking. The pre and post query expansion helps to improving the performance of English-Hindi CLIR system and based upon past experiences the proposed approach retrieves more relevant information. All experiments are performed on FIRE 2010 (Forum of Information Retrieval Evaluation) datasets. The experimental results show that the proposed approach gives equal/better performance of English-Hindi CLIR system compared to monolingual performance and also helps in overcoming existing problems and outperforms the existing English-Hindi CLIR system in terms of average precision.
机译：与单语性能相比，跨语言信息检索（CLIR）中的障碍问题是性能较差。 CLIR性能差的主要原因是查询词不匹配，查询词的多种表示形式和未翻译的查询词。在本文中，我们将努力解决已详细讨论的给定问题。为了提高CLIR系统的性能，需要解决这些限制。通过分析这些方法，提出了英语-印度语CLIR系统的体系结构。查询前和查询后扩展用于提高使用英语和印地语WordNet的英语-印地语CLIR系统的性能，使用初始查询的本地扩展，基于定义的预查询扩展和关键字排名。查询前和查询后扩展有助于提高English-Hindi CLIR系统的性能，并且基于过去的经验，所提出的方法可检索更多相关信息。所有实验均在FIRE 2010（信息检索论坛评估）数据集上进行。实验结果表明，与单语能力相比，该方法在英语-印度语CLIR系统上具有同等/更好的性能，并且在平均精度方面，还有助于克服现有问题并优于现有英语-印度语CLIR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