• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computers, Materials & Continua >Distant Supervised Relation Extraction with Cost-Sensitive Loss
【24h】

Distant Supervised Relation Extraction with Cost-Sensitive Loss

机译：具有成本敏感损失的遥远监督关系

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

Recently, many researchers have concentrated on distant supervision relation extraction (DSRE). DSRE has solved the problem of the lack of data for supervised learning, however, the data automatically labeled by DSRE has a serious problem, which is class imbalance. The data from the majority class obviously dominates the dataset, in this case, most neural network classifiers will have a strong bias towards the majority class, so they cannot correctly classify the minority class. Studies have shown that the degree of separability between classes greatly determines the performance of imbalanced data. Therefore, in this paper we propose a novel model, which combines class-to-class separability and cost-sensitive learning to adjust the maximum reachable cost of misclassification, thus improving the performance of imbalanced data sets under distant supervision. Experiments have shown that our method is more effective for DSRE than baseline methods.
机译：最近，许多研究人员集中在遥远的监督关系中（DSRE）。 DSRE已经解决了监督学习缺乏数据的问题，但是，DSRE自动标记的数据具有严重的问题，这是类别不平衡。来自多数类别的数据显然占据了数据集，在这种情况下，大多数神经网络分类器将对大多数类具有强烈偏见，因此无法正确分类少数阶层。研究表明，类之间的可分离程度大大决定了不平衡数据的性能。因此，在本文中，我们提出了一种新颖的模型，它将类级别的可分离性和成本敏感的学习结合起来调整最大的错误分类成本，从而提高了远处监控下的不平衡数据集的性能。实验表明，我们的方法对DSRE比基线方法更有效。

著录项

  • 来源
    《Computers, Materials & Continua》 |2019年第3期|1251-1261|共11页
  • 作者

    Daojian Zeng; Yao Xiao; Jin Wang; Yuan Dai; Arun Kumar Sangaiah;

  • 作者单位

    Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer & Communication Engineering Changsha University of Science & Technology Changsha 410004 China School of Computer & Communication Engineering Changsha University of Science & Technology Changsha 410004 China;

    Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer & Communication Engineering Changsha University of Science & Technology Changsha 410004 China School of Computer & Communication Engineering Changsha University of Science & Technology Changsha 410004 China;

    School of Computer & Communication Engineering Changsha University of Science & Technology Changsha 410004 China;

    Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer & Communication Engineering Changsha University of Science & Technology Changsha 410004 China School of Computer & Communication Engineering Changsha University of Science & Technology Changsha 410004 China;

    School of Computing Science and Engineering Vellore Institute of Technology (VIT) Tamil Nadu 637212 India;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Relation extraction; distant supervision; class imbalance; class separability; cost-sensitive;

    机译：关系提取;遥远的监督;班级不平衡;阶级可分离性;成本敏感;

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