Enhancing Question Generation in Bahasa Using Pretrained Language Models
Bibliographic record
Abstract
Automatic Question Generation (AQG) from text is difficult, especially in Indonesia, where research is scarce.Current research focuses on factual questions, leaving room for improvement.Previous studies used sequence-to-sequence models, which are effective for rule-based and cloze testing but rely on pre-existing rules.This article evaluates state-ofthe-art pre-trained models such as IndoBERT, IndoGPT, and IndoBART as well as classical models such as BiGRU, BiLSTM, and Transformer to fill this gap.This paper tests model question generation using SQuAD-ID, IDK-MRC, and TyDi-QA, three popular questionand-answer datasets.This study uses BLEU and ROUGE-L to evaluate each model's ability to generate meaningful queries from the provided settings.This research aims to understand AQG in Indonesian and evaluate model performance.Discusses the background of AQG research, model limitations, as well as research topics and hypotheses.The paper also analyzes the expected contributions, such as the effectiveness of the trained model and the architectural effects on the AQG process.This research improves natural language processing and question generation systems, especially for Indonesian.
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
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".