Transfer Learning Robustness in Multi-Class Categorization by Fine-Tuning Pre-Trained Contextualized Language Models

Abstract

This study compares the effectiveness and robustness of multi-class categorization of Amazon product data using transfer learning on pre-trained contextualized language models. Specifically, we fine-tuned BERT and XLNet, two bidirectional models that have achieved state-of-the-art performance on many natural language tasks and benchmarks, including text classification. While existing classification studies and benchmarks focus on binary targets, with the exception of ordinal ranking tasks, here we examine the robustness of such models as the number of classes grows from 1 to 20. Our experiments demonstrate an approximately linear decrease in performance metrics (i.e., precision, recall, $F_1$ score, and accuracy) with the number of class labels. BERT consistently outperforms XLNet using identical hyperparameters on the entire range of class label quantities for categorizing products based on their textual descriptions. BERT is also more affordable than XLNet in terms of the computational cost (i.e., time and memory) required for training. In all cases studied, the performance degradation rates were estimated to be 1% per additional class label.

arXiv commentPre-trained models and code available at https://github.com/artitw/text2class

References in corpus (5)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• Attending to Mathematical Language with Transformers
• Comparing Robustness of Pairwise and Multiclass Neural-Network Systems for Face Recognition
• Multi-Label Product Categorization Using Multi-Modal Fusion Models