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.

翻译：标签平滑是一种广泛应用于文本分类、图像分类和语音识别等领域的技术，以其有效对抗模型过拟合而闻名。然而，关于标签平滑如何增强文本情感分类的细粒度分析却很少。为填补这一空白，本文在八种文本情感分类数据集上，针对两种学习范式（从头训练与微调）下的三种深度学习架构（TextCNN、BERT和RoBERTa）进行了一系列深入分析。通过调整平滑参数，我们几乎在所有数据集上的每种模型架构中都取得了性能提升。我们进一步研究了标签平滑的优势，发现其能加速深度模型的收敛，并使不同标签的样本更易区分。