关系词非充盈态复句的特征融合CNN关系识别方法  

Relation Classification of Non-Saturated Chinese Compound Sentence via Feature Fusion CNN

作　　者：杨进才[1] 汪燕燕 曹元 胡金柱[1] YANG Jin-Cai;WANG Yan-Yan;CAO Yuan;HU Jin-Zhu(School of Computer,Central China Normal University,Wuhan 430079,China)

机构地区：[1]华中师范大学计算机学院,武汉430079

出　　处：《计算机系统应用》2020年第6期224-229,共6页Computer Systems & Applications

基　　金：国家社科基金(19BYY092)。

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.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 preexisting 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.

关 键 词：关系词非充盈态 复句语义关系 关系词 特征融合 卷积神经网络 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]