<![CDATA[This study analyzes the performance comparison between the Adam and RMSprop optimization algorithms in training a Bidirectional Long Short-Term Memory (Bi-LSTM) model with an Attention mechanism for Indonesian–Ngapak language translation. A parallel corpus of 23,592 sentence pairs was used, divided into training, validation, and testing datasets. The experimental results show that the Adam optimizer achieved faster convergence with a validation accuracy of 95.5%, validation loss of 0.43, and BLEU-1 to BLEU-4 scores of 0.8775, 0.8317, 0.7887, and 0.7393, respectively. In contrast, RMSprop reached 93.6% validation accuracy, 0.49 validation loss, and BLEU scores of 0.8284, 0.7636, 0.7034, and 0.6384. These results indicate that Adam offers higher efficiency and adaptability in optimizing neural parameters compared to RMSprop. Overall, this research contributes to the development of Neural Machine Translation for low-resource local languages while supporting the preservation of Ngapak as part of Indonesia’s linguistic heritage.]]>
Copyrights © 2025
