Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Attention-Guided Feature Fusion (AGFF) Model for Integrating Statistical and Semantic Features in News Text Classification

Mohammad Zare

TL;DR

The paper addresses the limitation of relying solely on statistical or semantic features for news text classification. It introduces the Attention-Guided Feature Fusion (AGFF) model, which fuses TF-IDF statistics with BiLSTM-based semantic representations through a per-dimension attention-guided gate to produce a fused feature z for classification. Empirical results on 20 Newsgroups and AG News show AGFF surpasses baselines including purely statistical and purely semantic models, with ablations validating the contribution of the fusion module and gate-based adaptivity. The approach balances interpretability and performance, offering a practical, lightweight alternative to large transformer models for hybrid text classification tasks. The work suggests that strategic integration of diverse feature types can yield robust improvements in real-world news categorization while maintaining reasonable computational costs.

Abstract

News text classification is a crucial task in natural language processing, essential for organizing and filtering the massive volume of digital content. Traditional methods typically rely on statistical features like term frequencies or TF-IDF values, which are effective at capturing word-level importance but often fail to reflect contextual meaning. In contrast, modern deep learning approaches utilize semantic features to understand word usage within context, yet they may overlook simple, high-impact statistical indicators. This paper introduces an Attention-Guided Feature Fusion (AGFF) model that combines statistical and semantic features in a unified framework. The model applies an attention-based mechanism to dynamically determine the relative importance of each feature type, enabling more informed classification decisions. Through evaluation on benchmark news datasets, the AGFF model demonstrates superior performance compared to both traditional statistical models and purely semantic deep learning models. The results confirm that strategic integration of diverse feature types can significantly enhance classification accuracy. Additionally, ablation studies validate the contribution of each component in the fusion process. The findings highlight the model's ability to balance and exploit the complementary strengths of statistical and semantic representations, making it a practical and effective solution for real-world news classification tasks.

Attention-Guided Feature Fusion (AGFF) Model for Integrating Statistical and Semantic Features in News Text Classification

TL;DR

The paper addresses the limitation of relying solely on statistical or semantic features for news text classification. It introduces the Attention-Guided Feature Fusion (AGFF) model, which fuses TF-IDF statistics with BiLSTM-based semantic representations through a per-dimension attention-guided gate to produce a fused feature z for classification. Empirical results on 20 Newsgroups and AG News show AGFF surpasses baselines including purely statistical and purely semantic models, with ablations validating the contribution of the fusion module and gate-based adaptivity. The approach balances interpretability and performance, offering a practical, lightweight alternative to large transformer models for hybrid text classification tasks. The work suggests that strategic integration of diverse feature types can yield robust improvements in real-world news categorization while maintaining reasonable computational costs.

Abstract

News text classification is a crucial task in natural language processing, essential for organizing and filtering the massive volume of digital content. Traditional methods typically rely on statistical features like term frequencies or TF-IDF values, which are effective at capturing word-level importance but often fail to reflect contextual meaning. In contrast, modern deep learning approaches utilize semantic features to understand word usage within context, yet they may overlook simple, high-impact statistical indicators. This paper introduces an Attention-Guided Feature Fusion (AGFF) model that combines statistical and semantic features in a unified framework. The model applies an attention-based mechanism to dynamically determine the relative importance of each feature type, enabling more informed classification decisions. Through evaluation on benchmark news datasets, the AGFF model demonstrates superior performance compared to both traditional statistical models and purely semantic deep learning models. The results confirm that strategic integration of diverse feature types can significantly enhance classification accuracy. Additionally, ablation studies validate the contribution of each component in the fusion process. The findings highlight the model's ability to balance and exploit the complementary strengths of statistical and semantic representations, making it a practical and effective solution for real-world news classification tasks.

Paper Structure

This paper contains 14 sections, 3 equations, 1 figure, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Text Classification Methods
  4. Feature Fusion and Hybrid Models
  5. Proposed Method (AGFF)
  6. Experimental Setup
  7. Datasets
  8. Baselines
  9. Implementation Details
  10. Results and Analysis
  11. Discussion
  12. Limitations
  13. Future Work
  14. Conclusion

Figures (1)

  • Figure 1: Architecture of the proposed AGFF model, which fuses statistical features (TF-IDF vector) with semantic features (BiLSTM with attention) using an attention-guided fusion module.