Hierarchical Multi-Task Learning for Fine-Grained and Coarse Text Classification
Frontiers in Interdisciplinary Applied Science · 2025
DOI: 10.71465/fias272 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Interdisciplinary Applied Science, 2025. Verfasst von Giulia Ferraro und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Text classification tasks often vary in granularity, with coarse labels capturing general topics and fine-grained labels capturing nuanced subcategories or sentiments. Traditional models trained separately on these classification levels struggle to leverage the hierarchical relationships between them. In this paper, we propose a hierarchical multi-task learning (HMTL) framework that jointly models coarse and fine-grained text classification tasks by aligning shared and task-specific layers in a hierarchical architecture. Our model exploits the inherent semantic dependencies between classification layers, enabling better generalization and improved performance on both tasks. Evaluations on benchmark datasets demonstrate that HMTL outperforms single-task baselines and flat multi-task models, particularly in domains with rich label hierarchies. The proposed framework provides a scalable and effective approach for tasks requiring contextual depth and label interdependence.
Zitieren
APA
Ferraro, G., & Benedetti, L. (2025). Hierarchical Multi-Task Learning for Fine-Grained and Coarse Text Classification. Frontiers in Interdisciplinary Applied Science. https://doi.org/10.71465/fias272
Vancouver
Ferraro G, Benedetti L. Hierarchical Multi-Task Learning for Fine-Grained and Coarse Text Classification. Frontiers in Interdisciplinary Applied Science. 2025. doi:10.71465/fias272
BibTeX
@article{Ferraro2025,
author = {Ferraro, Giulia and Benedetti, Luca},
title = {Hierarchical Multi-Task Learning for Fine-Grained and Coarse Text Classification},
journal = {Frontiers in Interdisciplinary Applied Science},
year = {2025},
doi = {10.71465/fias272}
}
EUVIMED