Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification
This work addresses robustness issues in sentiment analysis for applications like social media monitoring, though it is incremental as it builds on existing graph neural network methods.
The paper tackles the vulnerability of aspect-level sentiment classification models to parsing errors by proposing GraphMerge, a graph ensemble technique that combines dependency relations from multiple parsers before applying graph neural networks, resulting in improved performance on SemEval 2014 Task 4 and ACL 14 Twitter datasets without adding parameters.
Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks(GNN), but these approaches are usually vulnerable to parsing errors. To better leverage syntactic information in the face of unavoidable errors, we propose a simple yet effective graph ensemble technique, GraphMerge, to make use of the predictions from differ-ent parsers. Instead of assigning one set of model parameters to each dependency tree, we first combine the dependency relations from different parses before applying GNNs over the resulting graph. This allows GNN mod-els to be robust to parse errors at no additional computational cost, and helps avoid overparameterization and overfitting from GNN layer stacking by introducing more connectivity into the ensemble graph. Our experiments on the SemEval 2014 Task 4 and ACL 14 Twitter datasets show that our GraphMerge model not only outperforms models with single dependency tree, but also beats other ensemble mod-els without adding model parameters.