• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Natural language understanding and intelligent applications >Joint Event Extraction Based on Skip-Window Convolutional Neural Networks
【24h】

Joint Event Extraction Based on Skip-Window Convolutional Neural Networks

机译：基于跳窗卷积神经网络的联合事件提取

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

Traditional approaches to the task of ACE event extraction are either the joint model with elaborately designed features which may lead to generalization and data-sparsity problems, or the word-embedding model based on a two-stage, multi-class classification architecture, which suffers from error propagation since event triggers and arguments are predicted in isolation. This paper proposes a novel event-extraction method that not only extracts triggers and arguments simultaneously, but also adopts a framework based on convolutional neural networks (CNNs) to extract features automatically. However, CNNs can only capture sentence-level features, so we propose the skip-window convolution neural networks (S-CNNs) to extract global structured features, which effectively capture the global dependencies of every token in the sentence. The experimental results show that our approach outperforms other state-of-the-art methods.
机译：ACE事件提取任务的传统方法是具有精心设计的功能的联合模型（可能会导致泛化和数据稀疏性问题），或者是基于两阶段，多类分类架构的词嵌入模型，由于事件触发器和参数是独立预测的，因此不会从错误传播中产生。本文提出了一种新颖的事件提取方法，该方法不仅可以同时提取触发器和参数，而且还采用了基于卷积神经网络（CNN）的框架来自动提取特征。但是，CNN只能捕获句子级特征，因此我们提出了跳过窗口卷积神经网络（S-CNN）来提取全局结构化特征，从而有效地捕获了句子中每个标记的全局依赖性。实验结果表明，我们的方法优于其他最新方法。

著录项

  • 来源
  • 会议地点 Kunming(CN)
  • 作者

    Zhengkuan Zhang; Weiran Xu; Qianqian Chen;

  • 作者单位

    Automation School of Beijing University of Posts and Telecommunications, No. 10 Xitucheng Road, Haidian District, Beijing 100876, China;

    Beijing University of Posts and Telecommunications, Beijing, China;

    Emory University, Apt 2, 1535 N. Decatur Rd NE, Atlanta, GA 30307, USA;

  • 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