Comparative Analysis of Retriever and Reader for Open Domain Questions Answering on BPS Knowledge in Indonesian
Bibliographic record
Abstract
Enumerators from Badan Pusat Statistik (BPS) still often encounter problems in finding solutions to cases encountered during censuses or surveys. Even though knowledge lists have been created and collected in various systems such as QA and knowledge management systems, enumerators still need to find appropriate answers from long and complex knowledge search results. On the other hand, Open-domain Question Answering (OpenQA) is capable of identifying answers to natural questions based on large-scale documents. OpenQA has main components, namely Retriever and Reader. For Retriever tasks, Dense Retrieval (DR) is proven to outperform traditional sparse retrieval such as TF-IDF or BM25. However, other research actually shows that BM25 is superior to DR in terms of accuracy. In this study, we compared DR and BM25 separately and DR+BM25 as a retriever. Additionally, we combine and evaluate several enhanced language models as Readers. In this way, a model with the best combination of Retriever and Reader can be obtained to be implemented in search systems such as QA and knowledge management systems.
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 | 0.010 | 0.038 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.006 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.004 |
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".