The reusability of induced knowledge for the automatic semantic markup of taxonomic descriptions
Bibliographic record
Abstract
Abstract To automatically convert legacy data of taxonomic descriptions into extensible markup language (XML) format, the authors designed a machine‐learning‐based approach. In this project three corpora of taxonomic descriptions were selected to prove the hypothesis that domain knowledge and conventions automatically induced from some semistructured corpora (i.e., base corpora) are useful to improve the markup performance of other less‐structured, quite different corpora (i.e., evaluation corpora). The “structuredness” of the three corpora was carefully measured. Basing on the structuredness measures, two of the corpora were used as the base corpora and one as the evaluation corpus. Three series of experiments were carried out with the MARTT (markuper of taxonomic treatments) system the authors developed to evaluate the effectiveness of different methods of using the n‐gram semantic class association rules, the element relative position probabilities, and a combination of the two types of knowledge mined from the automatically marked‐up base corpora. The experimental results showed that the induced knowledge from the base corpora was more reliable than that learned from the training examples alone, and that the n‐gram semantic class association rules were effective in improving the markup performance, especially on the elements with sparse training examples. The authors also identify a number of challenges for any automatic markup system using taxonomic descriptions.
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
Direct model labels (unvalidated)
Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.
| Model arm | Categories | Study design | Confidence |
|---|---|---|---|
| gemma | no category Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Simulation or modeling | medium |
| gpt | no category Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Other design | low |
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 | 0.008 | 0.042 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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, unvalidatedLabeled directly by 2 models reading the full record.
The models disagree on parts of this classification; every voice is preserved in the section at the end of the page.
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".