The task of aspect-based sentiment analysis aims to identify sentiment polarities of given aspects in a sentence. Recent advances have demonstrated the advantage of incorporating the syntactic dependency structure with graph convolutional networks (GCNs). However, their performance of these GCN-based methods largely depends on the dependency parsers, which would produce diverse parsing results for a sentence. In this article, we propose a dual GCN (DualGCN) that jointly considers the syntax structures and semantic correlations. Our DualGCN model mainly comprises four modules: 1) SynGCN: instead of explicitly encoding syntactic structure, the SynGCN module uses the dependency probability matrix as a graph structure to implicitly integrate the syntactic information; 2) SemGCN: we design the SemGCN module with multihead attention to enhance the performance of the syntactic structure with the semantic information; 3) Regularizers: we propose orthogonal and differential regularizers to precisely capture semantic correlations between words by constraining attention scores in the SemGCN module; and 4) Mutual BiAffine: we use the BiAffine module to bridge relevant information between the SynGCN and SemGCN modules. Extensive experiments are conducted compared with up-to-date pretrained language encoders on two groups of datasets, one including Restaurant14, Laptop14, and Twitter and the other including Restaurant15 and Restaurant16. The experimental results demonstrate that the parsing results of various dependency parsers affect their performance of the GCN-based models. Our DualGCN model achieves superior performance compared with the state-of-the-art approaches. The source code and preprocessed datasets are provided and publicly available on GitHub (see https://github.com/CCChenhao997/DualGCN-ABSA).

中文翻译：

---

DualGCN：探索基于方面的情感分析的句法和语义信息。

基于方面的情感分析的任务旨在识别句子中给定方面的情感极性。最近的进展证明了将句法依赖结构与图卷积网络 (GCN) 相结合的优势。然而，这些基于 GCN 的方法的性能在很大程度上取决于依赖解析器，这会为一个句子产生不同的解析结果。在本文中，我们提出了一种联合考虑句法结构和语义相关性的双 GCN（DualGCN）。我们的 DualGCN 模型主要包括四个模块：1）SynGCN：SynGCN 模块不是显式编码句法结构，而是使用依赖概率矩阵作为图结构来隐式集成句法信息；2）SemGCN：我们设计了具有多头注意力的 SemGCN 模块，以利用语义信息增强句法结构的性能；3）正则化器：我们提出了正交和微分正则化器，通过限制 SemGCN 模块中的注意力分数来精确捕获单词之间的语义相关性；4) Mutual BiAffine：我们使用 BiAffine 模块来桥接 SynGCN 和 SemGCN 模块之间的相关信息。在两组数据集上与最新的预训练语言编码器进行了广泛的实验比较，一组包括 Restaurant14、Laptop14 和 Twitter，另一组包括 Restaurant15 和 Restaurant16。实验结果表明，各种依赖解析器的解析结果会影响其基于 GCN 的模型的性能。与最先进的方法相比，我们的 DualGCN 模型实现了卓越的性能。源代码和预处理数据集在 GitHub 上公开提供（参见 https://github.com/CCChenhao997/DualGCN-ABSA）。