Adversarial Training Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction
Yinuo Chen, Jing Zhao, Haoran Gao · 2023
The aim of this article is to propose an improved method for the ASTE task through the use of EMC-GCN and adversarial training. The authors suggest that by improving the robustness and accuracy of the EMC-GCN model, the overall performance on the task can be optimized. The article presents a series of experiments that validate the effectiveness of the proposed method. Specifically, the authors demonstrate that the use of adversarial training can optimize the loss function of the model, leading to significant improvements on the recall rate. Ultimately, this results in a more optimized and effective model that can achieve better performance on the comprehensive index F1 across multiple datasets. Overall, the proposed method provides a promising approach to improving the ASTE task through the use of EMC-GCN and adversarial training. By optimizing the performance of the model, this approach has the potential to facilitate more effective sentiment analysis and enhance our ability to understand and interpret complex linguistic data.