Improving Spell Checker Performance for Bahasa Indonesia Using Text Preprocessing Techniques with Deep Learning Models
Bibliographic record
Abstract
Spell checking capabilities, crucial within the domain of natural language processing, often encounter limitations in the context of Bahasa Indonesia due to data irregularities and the scarcity of high-quality training data.This study aims to enhance spell checker performance through the implementation of various text preprocessing techniques, including case folding, tokenization, stemming, and the removal of stop words.A Convolutional Neural Network (CNN), a deep learning model, was employed in this research to facilitate the overall process.The study utilized data gathered from social media communities, comprising a total of 10,000 entries.This data was divided into two subsets; 80% (8,000 entries) was allocated for training and the remaining 20% (2,000 entries) was designated for testing.A series of tests were conducted on datasets subject to different preprocessing approaches: without case folding, without stop words removal, without stemming, and with all text preprocessing stages implemented.The evaluation metrics employed in this study included accuracy, recall, precision, and the F1 score.The results demonstrated notable improvements in spell checker performance with appropriate text preprocessing.Specifically, the accuracy reached 0.86 for the dataset without stemming, 0.74 for the dataset without stop words removal, 0.7 for the dataset without case folding, and 0.89 for the dataset where all preprocessing stages were applied.These findings suggest that a comprehensive text preprocessing approach, paired with deep learning models, can significantly enhance spell checker performance for Bahasa Indonesia.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.005 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".