期刊文献+

双关系预测与特征融合的实体关系抽取模型

Entity relation extraction model with dual relation prediction and feature fusion
下载PDF
导出
摘要 现有分阶段解码的实体关系抽取模型仍存在着阶段间特征融合不充分的问题,会增大曝光偏差对抽取性能的影响。为此,提出一种双关系预测和特征融合的实体关系抽取模型(entity relation extraction model with dual relation prediction and feature fusion,DRPFF),该模型使用预训练的基于Transformer的双向编码表示模型(bidirectional encoder representation from transformers,BERT)对文本进行编码,并设计两阶段的双关系预测结构来减少抽取过程中错误三元组的生成。在阶段间通过门控线性单元(gated linear unit,GLU)和条件层规范化(conditional layer normalization,CLN)组合的结构来更好地融合实体之间的特征。在NYT和WebNLG这2个公开数据集上的试验结果表明,该模型相较于基线方法取得了更好的效果。 The staged decoding entity relation extraction model still has an insufficient feature fusion problem between stages,which increases the impact of exposure bias on the extraction performance.Herein,we propose a new entity relation extraction model with dual relation prediction and feature fusion(DRPFF).DRPFF uses a pretrained model of bidirectional encoder representation from transformers to encode texts,and a two-stage dual relation prediction structure is developed to reduce the false triples’generation.Between stages,a structure combining gated linear units and conditional layer normalization is utilized to fuse features better between entities.Experimental findings on two public datasets,NYT and WebNLG,demonstrate that the presented method has better results than the baseline methods.
作者 沈健 夏鸿斌 刘渊 SHEN Jian;XIA Hongbin;LIU Yuan(School of Artificial Intelligence and Computer,Jiangnan University,Wuxi 214122,China;Jiangsu Key Laboratory of Media Design and Software Technology,Wuxi 214122,China)
出处 《智能系统学报》 CSCD 北大核心 2024年第2期462-471,共10页 CAAI Transactions on Intelligent Systems
基金 国家自然科学基金项目(61972182)。
关键词 实体关系抽取 关系三元组 预训练模型 双关系预测 指针网络 特征融合 门控线性单元 条件层规范化 entity relation extraction relational triple BERT pretrained model dual relation prediction pointer network feature fusion gated linear unit conditional layer normalization
  • 相关文献

参考文献7

二级参考文献40

  • 1刘苏文,邵一帆,钱龙华.基于联合学习的生物医学因果关系抽取[J].中文信息学报,2020,34(4):60-68. 被引量:8
  • 2[1]PUSTEJOVSKY J,CASTANO,ZHANG J.Robust relational parsing over biomedical literature:extracting inhibit relations[C]// Proceedings of the Seventh Pacific Symposium on Bio-Computing.[S.l.],2002:362-373.
  • 3[2]LEROY G,CHEN H,MARTINEZ J D.A shallow parser based on closed-class words to capture relations in biomedical text[J].Journal of Biomedical Informatics,2003,36(3):145-158.
  • 4[3]PARK J C,KIM H S,KIM J J.Bidirectional incremental parsing for automatic pathway identification with combinatory categorical grammar[C]// Proceedings of the Pacific Symposium on Bio-Computing.Hawaii,USA,2001:396-407.
  • 5[4]TEMKIN J M,GILDER M R.Extraction of protein interaction information from unstructured text using a context-free grammar[J].Bioinformatics,2003,19:2046-2053.
  • 6[5]AHMED S T,CHINDAMBARAM D,DAVULCU H,et al.IntEx:a syntactic role driven protein-protein interaction extractor for bio-medical text[C]// Proceeding of the ACL-ISMB Workshop on Linking Biological Literature,Ontologies and Databases:Mining Biological Semantics.Detroit,Michigan,USA,2005:54-61.
  • 7[6]ONO T,HISHIGAKI H,TANIGAMIi A,et al.Automatic extraction of information on protein-protein interactions from the biological literature[J].Bioinformatics,2001,17 (2):155-161.
  • 8[7]HUANG M L,ZHU X Y,HAO Y,et al.Discovering patterns to extract protein-protein interactions from full texts[J].Bioinformatics,2004,20 (18):3604-3612.
  • 9[8]DAVID C,BEMARD B,WILLIAM L,et al.BioRAT:extracting biological information from full-length papers[J].Bioinformatics,2004,20(17):3206-3213.
  • 10[9]ANDRADE M A,VALENICA A.Automatic extraction of keywords from scientific text:application to the knowledge domain of protein families[J].Bioinformatic,1998,14(7):600-607.

共引文献54

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部