MORPHOLOGICALANALYSISFORAFAANOROMOOUSING DEEPLEARNINGAPPROACHES

Abstract

Afaan Oromoo, a widely spoken language in Ethiopia and neighbouring countries, presents unique challenges due to its complex morphological structure. Morphological analysis, which decomposes words into morphemes and assigns grammatical information, is a crucial natural language processing (NLP) task for this language. Previously some researchers conducted Afaan Oromoo morphological analysis using rule-based and traditional machine learning techniques. Rule-based methods are labour-intensive and time-consuming, especially with large datasets, while traditional machine learning approaches struggle with feature extraction and high-dimensional vector spaces, leading to information loss. This study addresses these challenges by employing deep learning architectures, including Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), Gated Recurrent Units (GRUs), and Bidirectional LSTMs (BiLSTMs) which are not applied for Afaan Oromoo morphological analysis yet. In the study, Comprehensive evaluations were conducted on a dataset consisting of 30,636 training words, 10,213 validation words, and 4,539 testing words. Performance metrics such as accuracy, precision, recall, and F1-score were used to evaluate the models. The evaluation results for each model are as follows: Normal CNN-LSTM with 70.94% accuracy, Word2Vec CNN-LSTM with 94.74% accuracy, Fast Text CNN-LSTM with 95.25% accuracy, Normal LSTM with 95.06% accuracy, Word2Vec LSTM with 93.89% accuracy, Fast Text LSTM with 90.02% accuracy, Normal GRU with 92.96% accuracy, Word2Vec GRU with 91.98% accuracy, Fast Text GRU with 91.32% accuracy, Normal BiLSTM with 95.24% accuracy, Word2Vec BiLSTM with 96.21% accuracy, and Fast Text BiLSTM with 96.43% accuracy. The Bidirectional LSTM (BiLSTM) models, particularly those using Word2Vec and Fast Text embeddings, demonstrated the highest accuracies, highlighting the effectiveness of deep learning approaches and neural word embedding techniques in Afaan Oromoo morphological analysis. This research not only advances the state-of-the-art in this domain but also provides a robust methodology for handling the morphological complexity of Afaan Oromoo using deep learning.