[1]任淑霞,刘旭琴.结合外部知识重构依赖矩阵的交互式图卷积网络[J].计算机技术与发展,2024,34(07):116-122.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0125]
　REN Shu-xia,LIU Xu-qin.An Interactive Graph Convolutional Network of Reconstructing Dependence Matrix with External Knowledge[J].,2024,34(07):116-122.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0125]
点击复制

结合外部知识重构依赖矩阵的交互式图卷积网络

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年07期
页码:
116-122
栏目:
人工智能
出版日期:
2024-07-10

文章信息/Info

Title:
An Interactive Graph Convolutional Network of Reconstructing Dependence Matrix with External Knowledge
文章编号:
1673-629X(2024)07-0116-07
作者:
任淑霞; 刘旭琴
天津工业大学 软件学院,天津 300387
Author(s):
REN Shu-xia; LIU Xu-qin
School of Software,Tianjin Polytechnic University,Tianjin 300387,China
关键词:
位置信息; 外部知识; 交互网络; 图卷积网络; 方面级情感分析
Keywords:
location information; external knowledge; interactive network; GCN; aspect-based sentiment analysis
分类号:
TP391.1
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0125
摘要:
方面级情感分析旨在预测给定句子中特定方面的情感极性。 然而,现有大多数研究在对模型改进的过程中忽略 了外部知识的有效利用,导致模型无法准确识别方面词的情感极性。 另外,仅仅考虑有限的上下文信息可能会使得模型在分析方面词时忽略其在句子中的重要性和影响。 基于此,提出了一种结合外部知识构建依赖增强矩阵的图卷积网络模型的方法(Dependency Enhancement Matrix GCN,DEMGCN)。 该方法首先将词嵌入和位置嵌入进行融合,得到包含位置信息的句子特征向量;同时引入情感常识信息对原始依赖矩阵进行扩展,形成新的依赖增强矩阵 DEM,这在一定程度上突出了情感词的权重信息,并且弥补了原始依赖树无法捕获边缘标签的不足。 此外,构建了一个信息交互网络( Information Interaction Network,IIN),通过方面词与上下文之间的交互来提取全局的句子信息。 最后,在 5 个基准数据集上的实验结果显示,与基线模型相比 DEMGCN 在准确率和 Macro-F1 上分别提高了 1 ~ 2 百分点。
Abstract:
Aspect-based sentiment analysis aims to predict the emotional polarity of a particular aspect in a given sentence. However,most of the existing researches ignore the effective use of external knowledge in the process of improving the model,which leads to the failure of the model to accurately identify the affective polarity of aspect words. In addition, considering only limited contextual information may cause the model to ignore the importance and influence of aspect words in the sentence. Based on this,we propose a graph convolutional network method combining external knowledge to construct dependency enhancement matrix. The word embeddings and position embeddings are fused to obtain sentence feature vectors containing position information firstly. At the same time,emotional common sense information is introduced to extend the original dependency matrix and form a new dependency enhancement matrix (DEM),which highlights the weight information of emotion words to a certain extent,and makes up for the shortage of the original de-pendency tree to capture edge labels. In addition, we construct an information interactive network ( IIN) to extract global sentence information through the interaction between aspect words and context. Finally,experimental results on five benchmark datasets show a 1 to 2 percentage points improvement in accuracy and Macro-F1,respectively,compared to the baseline model.

相似文献/References:

[1]杨宸 薛丹 周健.带空间特性的访问控制在汽车终端上的应用[J].计算机技术与发展,2012,(01):225.
　YANG Chen,XUE Dan,ZHOU Jian.Application of Role-Based Access Control with Spatial Character in Automobile Terminal[J].,2012,(07):225.
[2]许甜华,吴明礼.一种基于 TF-IDF 的朴素贝叶斯算法改进[J].计算机技术与发展,2020,30(02):75.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 016]
　XU Tian-hua,WU Ming-li.An Improved Naive Bayes Algorithm Based on TF-IDF[J].,2020,30(07):75.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 016]
[3]李 轩,李 静,王海燕.密集交通场景的目标检测算法研究[J].计算机技术与发展,2020,30(07):46.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 011]
　LI Xuan,LI Jing,WANG Hai-yan.Research on Object Detection Algorithm in Dense Traffic Scenes[J].,2020,30(07):46.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 011]

更新日期/Last Update: 2024-07-10