跳到主要导航 跳到搜索 跳到主要内容

Using Dilated Residual Network to Model Distantly Supervised Relation Extraction

  • Lei Zhan
  • , Yan Yang*
  • , Pinpin Zhu
  • , Liang He
  • , Zhou Yu
  • *此作品的通讯作者
  • East China Normal University
  • Ltd.
  • Shanghai Key Laboratory of Multidimensional Information Processing
  • University of California

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Distantly supervised relation extraction has been widely used to find relational facts in the text. However, distant supervision inevitably brings in noise that can lead to a bad relation contextual representation. In this paper, we propose a deep dilated residual network (DRN) model to address the noise of in distantly supervised relation extraction. Specifically, we design a module which employs dilated convolution in cascade to capture multi-scale context features by adopting multiple dilation rates. By combining them with residual learning, the model is more powerful than traditional CNN model. Our model significantly improves the performance for distantly supervised relation extraction on the large NYT-Freebase dataset compared to various baselines.

源语言英语
主期刊名Database Systems for Advanced Applications - DASFAA 2019 International Workshops
主期刊副标题BDMS, BDQM, and GDMA, Proceedings
编辑Guoliang Li, Jun Yang, Joao Gama, Juggapong Natwichai, Yongxin Tong
出版商Springer Verlag
500-504
页数5
ISBN(印刷版)9783030185893
DOI
出版状态已出版 - 2019
活动24th International Workshops on Database Systems for Advanced Applications, DASFAA 2019: BDMS, BDQM, and GDMA - Chiang Mai, 泰国
期限: 22 4月 201925 4月 2019

出版系列

姓名Lecture Notes in Computer Science
11448 LNCS
ISSN(印刷版)0302-9743
ISSN(电子版)1611-3349

会议

会议24th International Workshops on Database Systems for Advanced Applications, DASFAA 2019: BDMS, BDQM, and GDMA
国家/地区泰国
Chiang Mai
时期22/04/1925/04/19

学术指纹

探究 'Using Dilated Residual Network to Model Distantly Supervised Relation Extraction' 的科研主题。它们共同构成独一无二的学术指纹。

引用此