EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid attention-based multi-class classification of Ethiopian legal texts using deep learning

Amlakie Aschale Alemu iD, Malefia Demilie Melese, Daniel Arega Mengesha, Misganaw Aguate Widneh

PLOS One · 13.05.2026 · 21 (5) · e0348805

DOI: 10.1371/journal.pone.0348805 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 13.05.2026. Verfasst von Amlakie Aschale Alemu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Electrical and Computer Engineering, Gafat Institute of Technology, Debre Tabor University, Debre Tabor, Ethiopia. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The exponential growth of legal documents in Ethiopia has created an urgent need for efficient and accurate automated classification systems tailored to the country’s unique linguistic and legal contexts. This study presents an enhanced deep learning approach for multi-class classification of Ethiopian legal texts by leveraging deep neural architectures integrated with attention mechanisms. In this study, we proposed Hybrid deep learning algorithms. CNN, CNN + BiGRU and CNN + BiLSTM with and without an attention-based neural architecture that dynamically focuses on the most important textual features. The proposed hybrid architecture integrates hybrid models with an attention mechanism, allowing the model to capture contextual dependencies which is crucial in legal language understanding. Extensive experiments on a curated dataset of Ethiopian legal texts across multiple classes demonstrate significant improvements on multiple hybrid models like, CNN, CNN + BiGRU and CNN + BiLSTM integrated with Attention mechanism. Model performance is evaluated using an evaluation metrics of precision, recall, F1-score, and accuracy, with evaluation strategies like, 10-fold cross-validation and 80:20 train-test-split which showed notable gains in classification effectiveness. The experimental results show that CNN + BiLSTM with Self-Attention scores 99.53, 99.25, 99.37 and 99.38 for precision, recall, F1-score, and accuracy respectively with 80:20 train-test-split and 99, 98.99, 98.99, and 98.98 for precision, recall, F1-score, and accuracy respectively with 10-fold cross-validation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningClassification AlgorithmsEthiopiaConvolutional Neural NetworksHumansAlgorithmsAttention

Autor:innen und Institutionen

  • Electrical and Computer Engineering, Gafat Institute of Technology, Debre Tabor University, Debre Tabor, Ethiopia.
  • Department of Information Technology, Gafat Institute of Technology, Debre Tabor University, Debre Tabor, Ethiopia.

ORCID-Profile: Amlakie Aschale Alemu

Zitieren

APA

Alemu, A. A., Melese, M. D., Mengesha, D. A., & Widneh, M. A. (2026). Hybrid attention-based multi-class classification of Ethiopian legal texts using deep learning. PLOS One, 21(5), e0348805. https://doi.org/10.1371/journal.pone.0348805

Vancouver

Alemu AA, Melese MD, Mengesha DA, Widneh MA. Hybrid attention-based multi-class classification of Ethiopian legal texts using deep learning. PLOS One. 2026;21(5):e0348805. doi:10.1371/journal.pone.0348805

BibTeX
@article{Alemu2026,
  author = {Alemu, Amlakie Aschale and Melese, Malefia Demilie and Mengesha, Daniel Arega and Widneh, Misganaw Aguate},
  title = {Hybrid attention-based multi-class classification of Ethiopian legal texts using deep learning},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0348805},
  doi = {10.1371/journal.pone.0348805}
}
Kostenlos starten →