###
计算机系统应用:2020,29(6):224-229
本文二维码信息
码上扫一扫!
关系词非充盈态复句的特征融合CNN关系识别方法
(华中师范大学 计算机学院, 武汉 430079)
Relation Classification of Non-Saturated Chinese Compound Sentence via Feature Fusion CNN
(School of Computer, Central China Normal University, Wuhan 430079, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 79次   下载 77
投稿时间:2019-09-10    修订日期:2019-10-10
中文摘要: 汉语文章中复句占多数, 复句关系类别的识别是对复句分句之间的语义关系的甄别, 是分析复句语义的关键. 在关系词非充盈态复句中, 部分关系词缺省, 因此, 不能通过关系词搭配的规则来对非充盈态复句进行类别识别, 且通过人工分析分句的特征进行类别识别费时费力. 本文以二句式非充盈态复句为研究对象, 采用在卷积神经网络中融合关系词特征的FCNN模型, 尽可能减少对语言学知识和语言规则的依赖, 通过学习自动分析两个分句之间语法语义等特征, 从而识别出复句的关系类别. 使用本文提出的方法对复句关系类别识别准确率达97%, 实验结果证明了该方法的有效性.
Abstract:In Chinese essay, compound sentences are the majority. Recognition of relation category is screening for semantic relation of clauses in a compound sentence, and it is the key to analyze the meaning of the whole compound sentences. In a non-saturated compound sentence, the relation words are absent. So, the non-saturated compound sentence can not be classified by the features of the relation word collocation. In this work, an unbalanced corpus of non-saturated compound sentences with two clauses is taken as the research object. This study proposes a convolutional neural network for relation classification that automatically learns features from two clauses and minimizes the dependence on pre-existing natural language processing tools and language rules. The model fuses the features of relation to improve the performance. The experimental results show that the accuracy is 97% and that the proposed model outperforms the best baseline systems with sentence level features.
文章编号:7369     中图分类号:    文献标志码:
基金项目:国家社科基金(19BYY092)
引用文本:
杨进才,汪燕燕,曹元,胡金柱.关系词非充盈态复句的特征融合CNN关系识别方法.计算机系统应用,2020,29(6):224-229
YANG Jin-Cai,WANG Yan-Yan,CAO Yuan,HU Jin-Zhu.Relation Classification of Non-Saturated Chinese Compound Sentence via Feature Fusion CNN.COMPUTER SYSTEMS APPLICATIONS,2020,29(6):224-229

用微信扫一扫

用微信扫一扫