Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification
This work provides incremental insights into label smoothing for researchers in text sentiment classification, offering practical benefits like faster convergence and better label separation.
The paper tackled the lack of fine-grained analysis on how label smoothing enhances text sentiment classification by conducting in-depth experiments on eight datasets and three deep learning architectures, achieving improved performance on almost all datasets through parameter tuning.
Label smoothing is a widely used technique in various domains, such as text classification, image classification and speech recognition, known for effectively combating model overfitting. However, there is little fine-grained analysis on how label smoothing enhances text sentiment classification. To fill in the gap, this article performs a set of in-depth analyses on eight datasets for text sentiment classification and three deep learning architectures: TextCNN, BERT, and RoBERTa, under two learning schemes: training from scratch and fine-tuning. By tuning the smoothing parameters, we can achieve improved performance on almost all datasets for each model architecture. We further investigate the benefits of label smoothing, finding that label smoothing can accelerate the convergence of deep models and make samples of different labels easily distinguishable.