首页|融合特征编码和短语交互感知的隐式篇章关系识别

融合特征编码和短语交互感知的隐式篇章关系识别

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
隐式篇章关系识别难度大、普遍性高.从论元编码和论元交互角度入手,提出了一种融合特征编码和短语交互感知的隐式篇章关系识别模型.该模型兼顾了论元本身特征和论元间交互特征的作用,并分别进行了优化.论元编码部分整合了双向长短时记忆网络和循环注意力卷积神经网络,能够更全面地捕获论元全局和局部特征;论元交互部分从短语层级考虑论元间的语义关系建模,构建了短语级交互注意力机制,并利用神经张量网络深入挖掘其中的关系模式,更能体现出论元间潜在的更深层次的关联关系.在宾州篇章树库数据集上的实验结果表明,该模型F1值均优于其他模型.
Implicit Discourse Relation Recognition Integrating Feature Coding and Phrase Interaction Perception
Implicit discourse relation recognition is a challenging task because of its difficulty and universality.From the perspective of argument coding and argument interaction,an implicit discourse relation recognition model integrating feature coding and phrase interaction perception is proposed.The model considers both the characteristics of argument it-self and the interaction characteristics between arguments,and optimizes separately.The part of argument coding incorpo-rates bidirectional long short-term memory(BiLSTM)and recurrent attention convolution neural network(RACNN),which can capture global and local features of arguments in a more comprehensive way;in the part of argument interaction,the se-mantic relationship between arguments is modeled from phrase level,and a mechanism of phrase-level interactive attention is constructed.Also,neural tensor network(NTN)is used to dig into the relational pattern,which can better reflect the po-tential deeper relational relationship between arguments.Experimental results on penn discourse treebank(PDTB)dataset show that the F1 values of this model are superior to other comparison models.

implicit discourse relation recognitionbidirectional long short-term memoryrecurrent attention convo-lution neural networkphrase-level interactive attentionneural tensor network

王秀利、金方焱

展开 >

中央财经大学信息学院,北京 102206

国家金融安全教育部工程研究中心,北京 102206

隐式篇章关系识别 双向长短时记忆网络 循环注意力卷积神经网络 短语级交互注意力 神经张量网络

教育部哲学社会科学研究重大课题攻关项目中央财经大学新兴交叉学科建设项目

22JZD011

2024

10.12263/DZXB.20220246

电子学报
中国电子学会

电子学报

CSTPCD北大核心
影响因子：1.237
ISSN：0372-2112
年,卷(期)：2024.52(4)