A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification
This work addresses the problem of model interpretability for researchers and practitioners in NLP, though it is incremental as it builds on existing attention mechanisms.
The paper tackles the challenge of explainability in attention-based deep learning models for NLP by proposing a two-tier attention architecture, achieving competitive performance on news classification tasks with two large corpora.
Many recent deep learning-based solutions have widely adopted the attention-based mechanism in various tasks of the NLP discipline. However, the inherent characteristics of deep learning models and the flexibility of the attention mechanism increase the models' complexity, thus leading to challenges in model explainability. In this paper, to address this challenge, we propose a novel practical framework by utilizing a two-tier attention architecture to decouple the complexity of explanation and the decision-making process. We apply it in the context of a news article classification task. The experiments on two large-scaled news corpora demonstrate that the proposed model can achieve competitive performance with many state-of-the-art alternatives and illustrate its appropriateness from an explainability perspective.