Bibliographic record
Abstract
Our Genomics experiments mainly focus on addressing four problems in biomedical information retrieval. The four problems are: (1) how to deal with synonyms? (2) how to deal with the frequent use of acronyms? (3) how to deal with homonyms? (4) how to deal with the document-level retrieval, passagelevel retrieval and aspect-level retrieval? In particular, we use the automatic query expansion algorithm proposed at TREC 2005 to construct structured queries for document-level retrieval and we also apply several data mining techniques for passage-level retrieval and aspect-level retrieval. The mean average precisions (MAP) for our automatic run “york06ga1 ” are 0.3365 at the document-level retrieval, 0.0197 at the passage-level retrieval and 0.1084 at the aspect-level retrieval. The evaluation results show that the automatic query expansion algorithm is effective for improving document-level retrieval performance. However, our retrieval performance on passage-level and aspect-level is poor. One possible reason is that we did not follow the TREC 2006 Genomics track protocol regarding the calculation of passage measures correctly. Therefore, we built a completely wrong index for the passage-level retrieval. Since our aspectlevel retrieval is based on the results obtained from our passage level retrieval, the results thus obtained are sub-optimal. 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 | 0.016 | 0.022 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.005 | 0.005 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.032 | 0.022 |
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".