Les atouts multiples de la lemmatisation : l'exemple du latin
Bibliographic record
Abstract
Based on the long experience of LASLA (Liège) and its Latin text data bank, tbis paper aims to exemplify the usefulness of lemmatization and morphological analysis for text corpus studies (occurrences queries, statistical lists and tests).Lemmatization brings linguistic accuracy of data and results, morphological analysis opens up richer directions.Limits of tbis melhod are the lack of syntactical analysis (parsing).' RésuméEn se fondant sur la longue et riche expérience du LASLA (Liège) et sur la banque de textes latins qu'il a lemmatisée, il est ici question de montrer l'utilité que présentent la lemmatisation, mais aussi l'analyse morphologique des formes textuelles, pour les études de corpus textuels et linguistiques, notamment la recherche d'occurrences, les relevés statistiques et l'application de tests statistiques.Ces atouts sont, dans le cas de la lemmatisation, une précision linguistique des données manipulées et des résultats produits bien plus grande que dans l'exploitation des seules formes textuelles: pour l'analyse morphologique, richesse de la valeur ajoutée et ouvenure de perspectives.Plusieurs exemples illustrent non seulement les avantages, mais aussi 'es limites d'un codage purement lexical et morphologique, mais non syntaxique.
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 | 0.005 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.039 | 0.014 |
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".