Indexing low frequency information for question answering
Bibliographic record
Abstract
This paper presents our experiments with a low-frequency approach to information retrieval for question answering over a small, closed domain corpus and a variety of question types. With a corpus of 255 questions categorized into simple, average and challenging, we compared the performance of our question answering system (QASCU) when used with two different information retrieval systems, Lucene and BioKI. Lucene uses a standard tf.idf weighting scheme on documents, while BioKI uses a weighted keyword occurrence optimization scheme on paragraphs, that does not bias against low-frequency terms. While IR with Lucene yields better IR results at the document level than BioKI, running QASCU on BioKI output achieves higher precision. This indicates that for closed domain QA with an IR component, the basic F-measure performance of the IR component at the document level is not necessarily indicative of the overall performance. We contend that the findings are relevant also to retrieval from video, text, and sound collections that usually feature low redundancy in the text snippets used for retrieval. 1.
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 | 0.007 | 0.034 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.007 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 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".