Comparative Analysis of Adam and RMSprop Optimizers on Bi-LSTM Models for Indonesian–Ngapak Translation
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.019 | 0.015 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it