基于带噪观测的远监督神经网络关系抽取
作者:
作者单位:

作者简介:

叶育鑫(1981-),男,吉林长春人,博士,教授,博士生导师,CCF专业会员,主要研究领域为人工智能,信息抽取;王璐(1988-),女,博士后,主要研究领域为非参数模型,生物统计;薛环(1992-),男,硕士生,主要研究领域为远监督关系抽取;欧阳丹彤(1968-),女,博士,教授,博士生导师,CCF高级会员,主要研究领域为自动推理,模型诊断.

通讯作者:

欧阳丹彤,E-mail:ouyd@jlu.edu.cn

中图分类号:

TP181

基金项目:

国家自然科学基金(61672261,61872159)


Distant Supervision Neural Network Relation Extraction Base on Noisy Observation
Author:
Affiliation:

Fund Project:

National Natural Science Foundation of China (61672261, 61872159)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    远监督关系抽取的最大优势是通过知识库和自然语言文本的自动对齐生成标记数据.这种简单的自动对齐机制在将人从繁重的样本标注工作中解放出来的同时,不可避免地会产生各种错误数据标记,进而影响构建高质量的关系抽取模型.针对远监督关系抽取任务中的标记噪声问题,提出"最终句子对齐的标签是基于某些未知因素所生成的带噪观测结果"这一假设.并在此假设的基础上,构建由编码层、基于噪声分布的注意力层、真实标签输出层和带噪观测层的新型关系抽取模型.模型利用自动标记的数据学习真实标签到噪声标签的转移概率,并在测试阶段,通过真实标签输出层得到最终的关系分类.随后,研究带噪观测模型与深度神经网络的结合,重点讨论基于深度神经网络编码的噪声分布注意力机制以及深度神经网络框架下不均衡样本的降噪处理.通过以上研究,进一步提升基于带噪观测远监督关系抽取模型的抽取精度和鲁棒性.最后,在公测数据集和同等参数设置下进行带噪观测远监督关系抽取模型的验证实验,通过分析样本噪声的分布情况,对在各种样本噪声分布下的带噪观测模型进行性能评价,并与现有的主流基线方法进行比较.结果显示,所提出的带噪观测模型具有更高的准确率和召回率.

    Abstract:

    The great advantage of distant supervision relation extraction is to generate labeled data automatically through knowledge bases and natural language texts. This simple automatic alignment mechanism liberates people from heavy labeling work, but inevitably produces various incorrect labeled data meanwhile, which would have an influential effect on the construction of high-quality relation extraction models. To handle noise labels in the distant supervision relation extraction, here it is assumed that the final label of sentence is based on noisy observations generated by some unknown factors. Based on this assumption, a new relation extraction model is constructed, which consists of encoder layer, attention based on noise distribution layer, real label output layer, and noisy observation layer. In the training phase, transformation probabilities are learned from real label to noisy label by using automatically labeled data, and in the testing phase, the real label is obtained through the real label output layer. This study proposes to combine the noise observation model with deep neural network. The attention mechanism of noise distribution is focused based on deep neural network, and unbalanced samples are denoised of under the framework of deep neural network, aiming to further improve the performance of distant supervision relation extraction based on noisy observation. To examine its performance, the proposed method is applied to a public dataset. The performance of distant supervision relation extraction model is evaluated under different distribution families. The experimental results illustrate the proposed method is more effective with higher precision and recall, compared to the existing methods.

    参考文献
    相似文献
    引证文献
引用本文

叶育鑫,薛环,王璐,欧阳丹彤.基于带噪观测的远监督神经网络关系抽取.软件学报,2020,31(4):1025-1038

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-05-31
  • 最后修改日期:2019-07-29
  • 录用日期:
  • 在线发布日期: 2020-01-14
  • 出版日期: 2020-04-06
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号