Dom/anonymisation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(phase2): Multi-signal NER — BDPM gazetteers, confiance EDS, safe patterns, GLiNER

Browse Source 
Chantier 1: Intégration BDPM (5737 médicaments officiels) dans medication whitelist
Chantier 2: Safe patterns contextuels (dosages mg/mL/cpr, formes pharma, même ligne)
Chantier 3: Scores de confiance NER réels (edsnlp 0.20 ner_confidence_score)
Chantier 4: GLiNER zero-shot (urchade/gliner_multi_pii-v1) en vote croisé
Chantier 5: Scripts export silver annotations + fine-tuning CamemBERT-bio

0 fuite, 0 régression, -18 FP supplémentaires éliminés.
Sécurité: GLiNER ne peut rejeter que si confiance NER < 0.70.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Domi31tls
2026-03-09 12:01:46 +01:00
parent 782551c1c6
commit 26ac02b0cb
16 changed files with 6431 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
regression_tests/baseline/trackare-14025311-23034958_14025311_23034958.pseudonymise.txt
View File

@@ -779,7 +779,7 @@ Gelule(s)
[NOM]
[NOM]
[NOM]
[NOM] GEL
0,5 GEL
- Matin soir (8h -
19h) Normal
27/02/2023 18 : 40