A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification

TL;DR

This paper introduces a bi-level attention framework for news classification that enhances model explainability without sacrificing competitive performance, addressing the complexity challenge of deep learning models in NLP.

Contribution

It proposes a novel two-tier attention architecture that decouples explanation from decision-making in deep learning models for news classification.

Findings

Achieves competitive accuracy with state-of-the-art models

Improves explainability of attention mechanisms

Effective on large-scale news datasets

Abstract

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.