• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Swiss Conference on Data Science >APCNN: Tackling Class Imbalance in Relation Extraction through Aggregated Piecewise Convolutional Neural Networks
【24h】

APCNN: Tackling Class Imbalance in Relation Extraction through Aggregated Piecewise Convolutional Neural Networks

机译：APCNN：通过聚合分段卷积神经网络解决方面的阶级不平衡

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

One of the major difficulties in applying distant supervision to relation extraction is class imbalance, as the distribution of relations appearing in text is heavily skewed. This is particularly damaging for the multi-instance variant of relation extraction. In this work, we introduce a new model called Aggregated Piecewise Convolutional Neural Networks, or APCNN, to address this problem. APCNN relies on the combination of two neural networks, a novel objective function as well as oversampling techniques to tackle class imbalance. We empirically compare APCNN to state-of-the-art approaches and show that it outperforms previous multi-instance approaches on two standard datasets.
机译：在对关系提取施加遥远监督方面的一个主要困难是阶级不平衡，因为文中的关系分布严重倾斜。这对于关系提取的多实例变体来说特别损害。在这项工作中，我们介绍了一个名为汇总分段卷积神经网络或APCNN的新模型，以解决这个问题。 APCNN依赖于两个神经网络的组合，一种新颖的客观函数以及用于解决类别不平衡的过采样技术。我们凭证将APCNN与最先进的方法进行比较，并表明它始于两个标准数据集上的先前多实例方法。

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