Adaptive and multi-scale feature fusion for Chinese news headline classification

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: 1.28% and 0.55% accuracy improvement for ERNIE-AAFF-SECNN; 2.62% and 3.76% for ERNIE-MSSE-DSCNN

• Primary Outcome: Classification accuracy improvement over baseline models

• Nnt Or Sensitivity: Performance gains of 1-4% over TinyBERT baseline

• Confidence Interval: Not reported

Clinical Application

Limited to Chinese language processing applications No direct relevance to Australian healthcare practice, PBS, TGA, or RACGP guidelines Not applicable to clinical practice - computational linguistics study

Abstract

The rapid growth of online news has led to an explosion of short Chinese headlines, which often suffer from sparse features, limited context, and high ambiguity-posing significant challenges for accurate classification. To address these issues, this paper proposes two tailored deep learning models: ERNIE-AAFF-SECNN for large-scale datasets, which enhances semantic representation via adaptive fusion of multi-layer ERNIE features and improves local feature extraction with SE-empowered CNN; and ERNIE-MSSE-DSCNN for small-scale datasets, which integrates multi-scale SE attention, depthwise separable convolutions, and adversarial training to boost robustness under data scarcity. A large number of experiments have shown that both of these models have achieved the most advanced performance. It is worth noting that the accuracy of ERNIE-AAFF-SECNN on the THUCNews and Toutiao datasets is 1.28% and 0.55% higher, respectively, than that of the lightweight SOTA model TinyBERT. The accuracy of ERNIE-MSSE-DSCNN on a 10% training dataset is 2.62% and 3.76% higher than that of the lightweight SOTA model TinyBERT, respectively. It demonstrates outstanding effectiveness under both standard and low-resource Settings. These results demonstrate that targeted architectural enhancements-such as adaptive feature fusion and multi-scale attention with adversarial training-can significantly improve the accuracy and robustness of short-text classification in practical Chinese news applications.

References

1. 1.Yan, Y. (2026). Adaptive and multi-scale feature fusion for Chinese news headline classification. PLoS One. https://doi.org/10.1371/journal.pone.0345779