AI Insight
This study proposes hybrid deep learning architectures combining Convolutional Neural Networks (CNN) with Bidirectional Long Short-Term Memory (BiLSTM) or Bidirectional Gated Recurrent Units (BiGRU), augmented with attention mechanisms, for the automated multi-class classification of Ethiopian legal texts. The best-performing model, CNN + BiLSTM with Self-Attention, achieved an accuracy of 99.38% under an 80:20 train-test split and 98.98% under 10-fold cross-validation, consistently outperforming baseline architectures without attention mechanisms. The attention mechanism enabled the models to dynamically prioritize contextually relevant features within legal language, which the authors identify as a key factor in performance gains.
Why it matters
Automated classification of legal documents could significantly reduce the manual burden on legal professionals and institutions in Ethiopia, improving access to and organization of legal information in a linguistically specific context. The approach may also serve as a methodological template for similar low-resource language legal systems in other regions.
by Amlakie Aschale Alemu, Malefia Demilie Melese, Daniel Arega Mengesha, Misganaw Aguate Widneh
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.
Source: Hybrid attention-based multi-class classification of Ethiopian legal texts using deep learning