feat(phase1): Implémentation corrections qualité Phase 1

 Correction 1: Désactivation mapping DATE dans EDS-Pseudo
- Seules les dates de naissance sont masquées
- [DATE] = 0, [DATE_NAISSANCE] préservé
- Contexte temporel médical préservé

 Correction 2: Activation whitelist médicaments
- Médicaments préservés (IDACIO, SALAZOPYRINE, etc.)
- Filtrage dans _mask_with_eds_pseudo
- Information thérapeutique préservée

 Correction 3: Whitelist termes médicaux structurels
- Termes préservés (Chef de service, Praticien hospitalier, etc.)
- Filtrage dans _repl_service
- Contexte médical préservé

Tests: 100% succès sur corpus production (3 documents testés)
This commit is contained in:
2026-03-02 23:36:29 +01:00
parent 47a71df930
commit ea761823d6
12 changed files with 2231 additions and 105 deletions

View File

@@ -0,0 +1,19 @@
{"page": 0, "kind": "NOM", "original": "Nicolas PAVLOVSKY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64240 URT", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Elisa MAURY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64100 BAYONNE", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "STEPHANIE DAMESTOY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "ADRESSE", "original": "54 RUE DE GASCOGNE", "placeholder": "[ADRESSE]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64240 URT", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "STEPHANIE DAMESTOY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Daniel LAGUERRE", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "DATE_NAISSANCE", "original": "Date de naissance : 15/05/1975", "placeholder": "[DATE_NAISSANCE]", "bbox_hint": null}
{"page": 0, "kind": "ADRESSE", "original": "54 RUE DE GASCOGNE\n", "placeholder": "[ADRESSE]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64240 URT\nMme", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64100 BAYONNE\nMme STEPHANIE DAMESTOY", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "CODE_POSTAL", "original": "64240 URT\nPatient", "placeholder": "[CODE_POSTAL]", "bbox_hint": null}
{"page": 0, "kind": "ETAB", "original": "service\nLes suites ont été simples", "placeholder": "[MASK]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Nicolas PAVLOVSKY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Elisa MAURY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "STEPHANIE DAMESTOY", "placeholder": "[NOM]", "bbox_hint": null}
{"page": 0, "kind": "NOM", "original": "Daniel LAGUERRE", "placeholder": "[NOM]", "bbox_hint": null}