首页> 外文会议>Multilingual information access in South Asian languages >Two Models for the SMS-Based FAQ Retrieval Task of FIRE 2011
【24h】

Two Models for the SMS-Based FAQ Retrieval Task of FIRE 2011

机译:FIRE 2011基于SMS的FAQ检索任务的两种模型

获取原文
获取原文并翻译 | 示例

摘要

In this paper we propose a normalization model in order to standardize the terms used in SMS. For this purpose, we use a statistical bilingual dictionary calculated on the basis of the IBM-4 model for determining the best translation for a given SMS term. In order to compare our proposal with another method of document retrieval, we have submitted to the FIRE 2011 competition forum a second run which was obtained by using a probabilistic information retrieval model which employes the same statistical dictionaries used by our normalization method. The obtained results show that the normalization model greatly improves the performance of the probabilistic one. An interesting finding indicates that the Malayalam language is the one that seems to be better written in the SMS context, in comparison with the English and Hindi languages which were also evaluated in the framework of the monolingual, crosslingual and multilingual environments.
机译:在本文中,我们提出了一个标准化模型,以标准化SMS中使用的术语。为此,我们使用基于IBM-4模型计算的统计双语词典来确定给定SMS术语的最佳翻译。为了将我们的建议与另一种文档检索方法进行比较,我们已经向FIRE 2011竞争论坛提交了第二次测试,该测试是通过使用概率信息检索模型获得的,该模型采用了与我们的归一化方法相同的统计词典。所得结果表明,归一化模型极大地提高了概率模型的性能。一个有趣的发现表明,与英语和北印度语相比,马拉雅拉姆语在SMS上下文中似乎更好地书写,而英语和北印度语语言也在单语,跨语言和多语环境的框架中进行了评估。

著录项

  • 来源
  • 会议地点 Gandhinagar(IN);Bombay(IN)
  • 作者单位

    Faculty of Computer Science Benemerita Universidad Autonoma de Puebla, Mexico;

    Faculty of Computer Science Benemerita Universidad Autonoma de Puebla, Mexico;

    Faculty of Computer Science Benemerita Universidad Autonoma de Puebla, Mexico;

    Faculty of Computer Science Benemerita Universidad Autonoma de Puebla, Mexico;

    Faculty of Computer Science Benemerita Universidad Autonoma de Puebla, Mexico;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 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