Yinuo Chen
ABSTRACT
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.
- Wu Z , Ying C , Zhao F , Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction[J]. 2020.Google Scholar
Cross Ref
- Madry A , Makelov A , Schmidt L , Towards Deep Learning Models Resistant to Adversarial Attacks[J]. 2017.Google Scholar
- Dozat T , Manning C D . Deep Biaffine Attention for Neural Dependency Parsing[J]. 2016.Google Scholar
- Devlin J , Chang M W , Lee K , BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[J]. 2018.Google Scholar
- Yan H , Dai J , Ji T , A Unified Generative Framework for Aspect-Based Sentiment Analysis[J]. 2021.Google ScholarCross Ref
- Madry A , Makelov A , Schmidt L , Towards Deep Learning Models Resistant to Adversarial Attacks[J]. 2017.Google Scholar
- Peng H , Xu L , Bing L , Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment Analysis[C]// 2020:8600-8607.Google Scholar
- Liu F , Cohn T , Baldwin T . Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis[J]. 2018Google Scholar
- Wang W , Pan S J , Dahlmeier D , Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis[J]. 2016.Google ScholarCross Ref
- Yang B , Cardie C . Extracting opinion expressions with semi-Markov conditional random fields[C]// Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, 2012.Google Scholar
- Tang D , Qin B , Liu T . Aspect Level Sentiment Classification with Deep Memory Network[J]. 2016.Google ScholarCross Ref
- Hu M , Liu B . Mining and summarizing customer reviews[C]// Knowledge Discovery and Data Mining. ACM, 2004.Google Scholar
- Read J , Pfahringer B , Holmes G , Classifier Chains: A Review and Perspectives[J]. 2019.Google Scholar
- Mao Y , Shen Y , Yu C , A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis[J]. 2021.Google ScholarCross Ref
- Peng H , Xu L , Bing L , Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis[J]. arXiv, 2019.Google Scholar
- Wang F , Li Y , Zhang W , A More Fine-Grained Aspect-Sentiment-Opinion Triplet Extraction Task[J]. 2021.Google Scholar
Index Terms
- Adversarial Training Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction
Recommendations
A hybrid adversarial training for deep learning model and denoising network resistant to adversarial examples
AbstractDeep neural networks (DNNs) are vulnerable to adversarial attacks that generate adversarial examples by adding small perturbations to the clean images. To combat adversarial attacks, the two main defense methods used are denoising and adversarial ...
LADDER: Latent boundary-guided adversarial training
AbstractDeep Neural Networks (DNNs) have recently achieved great success in many classification tasks. Unfortunately, they are vulnerable to adversarial attacks that generate adversarial examples with a small perturbation to fool DNN models, especially in ...
Adversarial Convolutional Neural Network for Text Classification
EITCE '20: Proceedings of the 2020 4th International Conference on Electronic Information Technology and Computer EngineeringText classification is a fundamental task of natural language processing. The convolutional neural network (CNN) has been employed popularly and achieved excellent results on text classification. Nevertheless, the training parameters of CNN is prone to ...
Comments