Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation

Veyseh, Amir Pouran Ben; Nouri, Nasim; Dernoncourt, Franck; Tran, Quan Hung; Dou, Dejing; Nguyen, Thien Huu

doi:10.18653/v1/2020.findings-emnlp.407

Cited by 21 publications

(13 citation statements)

References 22 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4) RGCN. Veyseh et al (2020) [54] regulate the GCN-based representation vectors based on the dependency trees in order to benefit from the overall contextual importance scores of the words.…”

Section: Methodsmentioning

confidence: 99%

“…[60] use a memory network to cache the sentential representations into external memory and then calculate the attention with the target aspect. Recently, Veyseh et al (2020) [54] regulate the GCN-based representation vectors based on the dependency trees in order to benefit from the overall contextual importance scores of the words.…”

Section: Sentiment Analysis and Opinion Miningmentioning

confidence: 99%

“…We further fuse the dependency syntax for feature enhancement. Previous works for ABSA unfortunately merely make use of the syntactic dependency edge features (i.e., the tree structure) [18,27,31,54]. Without modeling the syntactic dependency labels attached to the dependency arcs, prior studies are limited by treating all word-word relations in the graph equally [16,19,20,23].…”

Section: Syntax Fusion Layermentioning

confidence: 99%

See 2 more Smart Citations

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

Fei

Chua

et al. 2022

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

Aspect-based sentiment analysis (ABSA) aims at automatically inferring the specific sentiment polarities towards certain aspects of products or services behind the social media texts or reviews, which has been a fundamental application to the real-world society. Within recent decade, ABSA has achieved extraordinarily high accuracy with various deep neural models. However, existing ABSA models with strong in-house performances may fail to generalize to some challenging cases where the contexts are variable, i.e., being low robustness to real-world environment. In this study, we propose to enhance the ABSA robustness by systematically rethinking the bottlenecks from all possible angles, including model, data and training. First, we strengthen the current best-robust syntax-aware models by further incorporating the rich external syntactic dependencies and the labels with aspect simultaneously with a universal-syntax graph convolutional network. In the corpus perspective, we propose to automatically induce high-quality synthetic training data with various types, allowing models to learn sufficient inductive bias for better robustness. Lastly, we based on the rich pseudo data perform adversarial training to enhance the resistance to the context perturbation, and meanwhile employ contrastive learning to reinforce the representations of instances with contrastive sentiments. Extensive robustness evaluations are conducted. The results demonstrate that our enhanced syntax-aware model achieves better robustness performances than all the state-of-the-art baselines. By additionally incorporating our synthetic corpus, the robust testing results are pushed with around 10% accuracy, which are then further improved by installing the advanced training strategies. In-depth analyses are presented for revealing the factors influencing the ABSA robustness.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Sentiment Analysis and Opinion Miningmentioning

confidence: 99%

Section: Syntax Fusion Layermentioning

confidence: 99%

See 1 more Smart Citation

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

Fei

Chua

et al. 2022

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

show abstract

“…The key idea of the model is to use a gating mechanism to filter out irrelevant information, thereby uncovering crucial information related to aspect words. This method not only improves the accuracy of information extraction, but also helps the model gain a more comprehensive understanding of important information related to specific aspects in the text, thereby enhancing its performance in relevant tasks [ 25 ]. Zhao et al construct a graph taking aspects as nodes, and apply graph convolutional networks to extract inter-aspect sentiment dependencies for analyzing different aspects.…”

Section: Related Workmentioning

confidence: 99%

Modeling Structured Dependency Tree with Graph Convolutional Networks for Aspect-Level Sentiment Classification

Zhao,

Yang,

et al. 2024

Sensors

View full text Add to dashboard Cite

Aspect-based sentiment analysis is a fine-grained task where the key goal is to predict sentiment polarities of one or more aspects in a given sentence. Currently, graph neural network models built upon dependency trees are widely employed for aspect-based sentiment analysis tasks. However, most existing models still contain a large amount of noisy nodes that cannot precisely capture the contextual relationships between specific aspects. Meanwhile, most studies do not consider the connections between nodes without direct dependency edges but play critical roles in determining the sentiment polarity of an aspect. To address the aforementioned limitations, we propose a Structured Dependency Tree-based Graph Convolutional Network (SDTGCN) model. Specifically, we explore construction of a structured syntactic dependency graph by incorporating positional information, sentiment commonsense knowledge, part-of-speech tags, syntactic dependency distances, etc., to assign arbitrary edge weights between nodes. This enhances the connections between aspect nodes and pivotal words while weakening irrelevant node links, enabling the model to sufficiently express sentiment dependencies between specific aspects and contextual information. We utilize part-of-speech tags and dependency distances to discover relationships between pivotal nodes without direct dependencies. Finally, we aggregate node information by fully considering their importance to obtain precise aspect representations. Experimental results on five publicly available datasets demonstrate the superiority of our proposed model over state-of-the-art approaches; furthermore, the accuracy and F1-score show a significant improvement on the majority of datasets, with increases of 0.74, 0.37, 0.65, and 0.79, 0.75, 1.17, respectively. This series of enhancements highlights the effective progress made by the STDGCN model in enhancing sentiment classification performance.

show abstract

“…(1) These methods rely mainly on the semantic representation of sentences and ignore the syntactic information of the sentences. Recent studies 6,7 has shown that the introduction of syntactic analysis has improved the effectiveness of natural language processing.…”

Section: Introductionmentioning

confidence: 99%

A text sentiment multi-classification method based on dual graph convolutional network

Gan,

Chen

2023

International Conference on Electronic Information Engineering and Data Processing (EIEDP 2023)

View full text Add to dashboard Cite

Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation

Cited by 21 publications

References 22 publications

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

Modeling Structured Dependency Tree with Graph Convolutional Networks for Aspect-Level Sentiment Classification

A text sentiment multi-classification method based on dual graph convolutional network

Contact Info

Product

Resources

About