...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of web semantics: >Curriculum learning for distant supervision relation extraction
【24h】

Curriculum learning for distant supervision relation extraction

机译：远程监督关系提取的课程学习

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

Relation extraction under distant supervision leverages the existing knowledge base to label data automatically, thus greatly reduced the consumption of human labors. Although distant supervision is an efficient method to obtain a large amount of labeled data, the training dataset labeled by distant supervision suffers from noise problem resulting in poor generalization ability of the relation extractor. To alleviate the noise problem, we propose a novel relation extraction method based on curriculum learning. Curriculum learning is utilized to guide the training process of relation extractor, specifically through the predefined curriculum-driven mentor network. Mentor network can dynamically adjust the weights of sentences during training, giving lower weights to noisy sentences and higher weights to truly labeled sentences. Relation extractor and mentor network are trained collaboratively to optimize joint objective. The experimental results show that the proposed method can improve the generalization ability of relation extractor in a noisy environment and obtains better performance for relation extraction.
机译：远程监督下的关系提取利用现有知识库自动标记数据，从而大大降低了人类劳动力的消费。虽然远程监督是获得大量标记数据的有效方法，但是遥远监督标记的训练数据集遭受噪声问题，导致关系提取器的普遍能力差。为了缓解噪声问题，我们提出了一种基于课程学习的新颖关系提取方法。课程学习用于指导关系提取器的培训过程，具体是通过预定义的课程驱动的导师网络。导师网络可以在训练期间动态调整句子的权重，给出嘈杂的句子和更高权重到真正标记的句子。关系提取器和导师网络正在合作培训，以优化联合目标。实验结果表明，该方法可以提高关系提取器在嘈杂环境中的泛化能力，并获得更好的关系提取性能。

著录项

  • 来源
    《Journal of web semantics:》 |2020年第3期|100559.1-100559.10|共10页
  • 作者

    Liu Qiongxin; Wang Peng; Wang Jiasheng; Ma Jing;

  • 作者单位

    Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Beijing 100081 China;

    School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China;

    School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China;

    School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China;

    School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China;

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

    Relation extraction; Curriculum learning; Mentor network;

    机译：关系提取;课程学习;导师网络;

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