{ "source_file": "CRH 23090597.pdf", "total_replacements": 420, "regex_replacements": 204, "ner_replacements": 18, "sweep_replacements": 198, "entities_found": [ { "original": "23090597", "replacement": "[EPISODE_1]", "source": "regex", "category": "episode" }, { "original": "23090597", "replacement": "[EPISODE_1]", "source": "regex", "category": "episode" }, { "original": "23090597", "replacement": "[EPISODE_1]", "source": "regex", "category": "episode" }, { "original": "23090597", "replacement": "[EPISODE_1]", "source": "regex", "category": "episode" }, { "original": "23090597", "replacement": "[EPISODE_1]", "source": "regex", "category": "episode" }, { "original": "23090597", "replacement": "[EPISODE_1]", "source": "regex", "category": "episode" }, { "original": "10100532760", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10100532760", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10100532760", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10100532760", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10100532760", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10100532760", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "fprevost@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "boui@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "dnivet@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "tkhuong-huu@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "aguilngar@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "fgoutorbe@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "mcboudier@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "mbrugel@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "mboube@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "faudemar@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "fprevost@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "boui@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "dnivet@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "tkhuong-huu@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "aguilngar@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "fgoutorbe@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "mcboudier@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "mbrugel@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "mboube@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "faudemar@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "fprevost@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "boui@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "dnivet@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "tkhuong-huu@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "aguilngar@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "fgoutorbe@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "mcboudier@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "mbrugel@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "mboube@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "faudemar@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "fprevost@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "boui@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "dnivet@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "tkhuong-huu@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "aguilngar@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "fgoutorbe@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "mcboudier@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "mbrugel@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "mboube@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "faudemar@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "fprevost@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "boui@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "dnivet@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "tkhuong-huu@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "aguilngar@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "fgoutorbe@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "mcboudier@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "mbrugel@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "mboube@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "faudemar@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "fprevost@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "boui@ch-cotebasque.fr", "replacement": "[EMAIL_2]", "source": "regex", "category": "email" }, { "original": "dnivet@ch-cotebasque.fr", "replacement": "[EMAIL_3]", "source": "regex", "category": "email" }, { "original": "tkhuong-huu@ch-cotebasque.fr", "replacement": "[EMAIL_4]", "source": "regex", "category": "email" }, { "original": "aguilngar@ch-cotebasque.fr", "replacement": "[EMAIL_5]", "source": "regex", "category": "email" }, { "original": "fgoutorbe@ch-cotebasque.fr", "replacement": "[EMAIL_6]", "source": "regex", "category": "email" }, { "original": "mcboudier@ch-cotebasque.fr", "replacement": "[EMAIL_7]", "source": "regex", "category": "email" }, { "original": "mbrugel@ch-cotebasque.fr", "replacement": "[EMAIL_8]", "source": "regex", "category": "email" }, { "original": "mboube@ch-cotebasque.fr", "replacement": "[EMAIL_9]", "source": "regex", "category": "email" }, { "original": "faudemar@ch-cotebasque.fr", "replacement": "[EMAIL_10]", "source": "regex", "category": "email" }, { "original": "[MEDECIN_32", "replacement": "[PERSONNE_1]", "source": "ner", "score": 0.855421245098114 }, { "original": "PATIENT", "replacement": "[PERSONNE_2]", "source": "ner", "score": 0.9085431694984436 }, { "original": "[MEDECIN", "replacement": "[PERSONNE_3]", "source": "ner", "score": 0.9871876835823059 }, { "original": "[MEDECIN_40", "replacement": "[PERSONNE_4]", "source": "ner", "score": 0.9260967969894409 }, { "original": "Grellety", "replacement": "[MEDECIN]", "source": "ner", "score": 0.9931332468986511 }, { "original": "[PATIENT", "replacement": "[PERSONNE_5]", "source": "ner", "score": 0.8426152467727661 }, { "original": "J. LOEB", "replacement": "[PERSONNE_6]", "source": "ner", "score": 0.9594755172729492 }, { "original": "MEDECIN_", "replacement": "[PERSONNE_7]", "source": "ner", "score": 0.8217464685440063 }, { "original": "[MEDECIN_", "replacement": "[PERSONNE_8]", "source": "ner", "score": 0.9736776947975159 }, { "original": "Thomas Grellety", "replacement": "[MEDECIN_2]", "source": "ner", "score": 0.9984971880912781 }, { "original": "[MEDEC", "replacement": "[PERSONNE_9]", "source": "ner", "score": 0.8172798156738281 }, { "original": "KHUONG HUU Tam A", "replacement": "[PERSONNE_10]", "source": "ner", "score": 0.9826402068138123 }, { "original": "M. [PATIENT", "replacement": "[PERSONNE_11]", "source": "ner", "score": 0.8104388117790222 }, { "original": "[MEDECIN_41", "replacement": "[PERSONNE_12]", "source": "ner", "score": 0.9439924359321594 }, { "original": "[PATIENT_", "replacement": "[PERSONNE_13]", "source": "ner", "score": 0.9318293333053589 }, { "original": "neau", "replacement": "[PERSONNE_14]", "source": "ner", "score": 0.8325887322425842 }, { "original": "MEDEC", "replacement": "[PERSONNE_15]", "source": "ner", "score": 0.811922550201416 }, { "original": "DARRIGADE Bernard", "replacement": "[PERSONNE_16]", "source": "ner", "score": 0.9893203973770142 } ] }