Journal of Computer Applications

    Next Articles

Dependency type and distance enhanced aspect based sentiment analysis model

  

  • Received:2024-08-05 Revised:2024-10-21 Online:2024-11-19 Published:2024-11-19
  • Supported by:
    Qingdao Science and Technology Benefiting the People Demonstration Project

依赖类型及距离增强的方面级情感分析模型

赵彪1,秦玉华1,田荣坤1,胡月航2,陈芳锐2   

  1. 1. 青岛科技大学
    2. 云南中烟工业有限责任公司
  • 通讯作者: 秦玉华
  • 基金资助:
    青岛市科技惠民示范项目

Abstract: In the field of aspect based sentiment analysis, existing dual channel models failed to comprehensively consider the different importance levels between grammar nodes, the additional noise introduced by global attention mechanism, and the existence of correlations between similar features. To address the above issues, a dual channel graph convolutional model enhanced by dependency type and dependency distance was proposed. Firstly, dependency types are introduced to measure the importance of neighbourhood nodes; Secondly, mask matrixes based on the dependency tree distance were constructed to filter unrelated noise; Finally, a supervised contrastive loss was introduced to facilitate the model to learn correlations between features that in the same kinds. The experimental results on multiple datasets showed that compared to baseline models, our model gains a better accurancy and macro_f1.

Key words: Aspect-based sentiment analysis, Graph convolutional network, Dependency type, Dependency tree distance, Supervised contrastive loss

摘要: 方面级情感分析领域中,同时提取语法、语义两种信息的双通道模型取得了一定的效果。然而,现有模型未能够考虑语法节点间的重要程度不同、全局范围下的注意力机制引入了额外噪声以及同类特征间存在一定关联性等问题。为解决以上问题,提出了一种依赖类型及距离增强的双通道图卷积模型。首先,在语法模块引入依赖类型以衡量不同邻近节点的重要程度;其次,以依赖树距离为依据构造掩码矩阵以过滤语法无关的噪声;最后,引入了一个有监督对比损失来促进模型学习同类特征间的关联性。在多个数据集上的实验结果表明,对于准确率和宏F1值两指标,本文模型的表现优于各基线模型。

关键词: 方面级别情感分析, 图神经网络, 依赖类型, 依赖树距离, 有监督对比损失

CLC Number: