College of Computing and Informatics
URI for this communityhttps://rps.wku.edu.et/handle/987654321/2333
College of Computing and Informatics
Browse
3 results
Search Results
Item DESIGN SOCIAL EVENT EXTRACTION MODEL FROM AMHARIC TEXTS USING DEEP LEARNING APPROACHES(Wolkite University, 2025-05-01) MIMI ADIMASU GODINESocial events play a crucial role in capturing societal trends, public opinions, and cultural activities. Extracting and analyzing social events from Amharic text can provide valuable insights into various domains. The extraction of social events from Amharic text poses significant challenges due to the complexity of the language and the unstructured nature of user-generated content. This study aims to develop an effective social event extraction model for Amharic text using deep learning approaches. This study used Yem zone social event datasets, total dataset size is 4,738 event records. By evaluating various feature extraction techniques, including Fast Text, Bi-grams, and Tri-grams, we identify the most suitable methods for enhancing event extraction accuracy. We implement several deep learning models, including LSTM, Bi-LSTM, GRU, Bi-GRU, and Simple-RNN, and assess their performance in extracting event trigger words. The results indicate that the GRU and Bi-GRU models consistently outperform their LSTM and Bi-LSTM counterparts, particularly when utilizing Tri-gram features. Notably, the Bi-GRU model achieves the highest accuracy of 1.00, underscoring the benefits of a bidirectional approach in capturing contextual information. This research contributes to the advancement of Amharic language processing, offering insights that can support various applications such as cultural studies, disaster management, and crisis response. Additionally, we introduce a social event extraction corpus for the Amharic language, paving the way for future research in this area.Item SENTENCE-LEVEL GRAMMAR CHECKER FOR KAMBAATISSA LANGUAGE USING DEEP LEARNING APPROACH(Wolkite University, 2023) TIHUN SEIFUIn the modern world, the most basic and culturally accepted means of communication is language, and the use of grammar is crucial to language fluency. Finding grammatical errors in natural language processing applications involves checking whether the words in a sentence conform to the predefined grammar rules for number, gender, tense, and the necessary information to convey the information in written language. Incorrect input sentences can have agreement problems, such as subject-verb, adjective-noun, and adverbverb agreement problems. This study developed a sentence-level grammar checker for the Kambaatissa language using a deep learning approach. In particular, we focus on implementations of gating methods such as the LSTM class and the more recently proposed GRU. For the development of the proposed model, Python programming languages and packages were used. Among the packages, the TensorFlow and Keras packages can effectively perform grammar error checking of the proposed model. GRU and LSTM test cases were used for evaluation. Finally, the test results show that the LSTM accuracy is 83% recall, 83% precision, 83%, f1_score is 83% and kappa score is 78%. The GRU performed 83% accuracy, 83% of recall, 83% precision and 83% f1_score and kappa score is 77%. The main challenge of this study was the rich and complex morphology of the Kambaatissa language and to find a sufficient amount of Kambaatissa sentence. The results of this study help to advance the Kambaatissa language's grammar checking technology. For writers, students, and language learners seeking to ensure that written text is grammatically correct and consistent, advanced grammar proofreading is an invaluable resource. Future research directions include expanding the coverage of the grammar checker to handle more complex grammatical constructions and integrating it with textual support models for wider usability.Item DEVELOPING SEMANTIC TEXTUAL SIMILARITY FOR GURAGIGNA LANGUAGE USING DEEP LEARNING APPROACH(WOLKITE UNIVERSITY, 2024-05-28) GETNET DEGEMUNatural language processing (NLP) is one part of how far the world has come in terms of technology. It is the process of teaching human language to machines and includes everything from Morphology Analysis to Pragmatic Analysis. Semantic Similarity is one of the highest levels of NLP. The Previous Semantic textual similarity (STS) studies have been conducted using from string-based similarity methods to deep learning methods. These studies have their limitations, and no research has been done for STS in the local language using deep learning. STS has significant advantages in NLP applications like information retrieval, information extraction, text summarization, data mining, machine translation, and other tasks. This thesis aims to present a deep learning approach for capturing semantic textual similarity (STS) in the Guragigna language. The methodology involves collecting a Guragigna language corpus and preprocessing the text data and text representation is done using the Universal Sentence Encoder (USE), along with word embedding techniques including Word2Vec and GloVe andmean Square Error (MSE) is used to measure the performance. In the experimentation phase, models like LSTM, Bidirectional RNN, GRU, and Stacked RNN are trained and evaluated using different embedding techniques. The results demonstrate the efficacy of the developed models in capturing semantic textual similarity in the Guragigna language. Across different embedding techniques, including Word2Vec, GloVe, and USE, the Bidirectional RNN model with USE embedding achieves the lowest MSE of 0.0950 and the highest accuracy of 0.9244. GloVe and Word2Vec embedding also show competitive performance with slightly higher MSE and lower accuracy. The Universal Sentence Encoder consistently emerges as the top-performing embedding across all RNN architectures. The research results demonstrate the effectiveness of LSTM, GRU, Bi RNN, and Stacked RNN models in measuring semantic textual similarity in the Garaging language