{ "source_file": "CRH 23138778.pdf", "total_replacements": 338, "regex_replacements": 152, "ner_replacements": 14, "sweep_replacements": 172, "entities_found": [ { "original": "10110601324", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10101096005", "replacement": "[RPPS_2]", "source": "regex", "category": "rpps" }, { "original": "10100163277", "replacement": "[RPPS_3]", "source": "regex", "category": "rpps" }, { "original": "10101639580", "replacement": "[RPPS_4]", "source": "regex", "category": "rpps" }, { "original": "10004606595", "replacement": "[RPPS_5]", "source": "regex", "category": "rpps" }, { "original": "10101480506", "replacement": "[RPPS_6]", "source": "regex", "category": "rpps" }, { "original": "10100858090", "replacement": "[RPPS_7]", "source": "regex", "category": "rpps" }, { "original": "10102268702", "replacement": "[RPPS_8]", "source": "regex", "category": "rpps" }, { "original": "10102272209", "replacement": "[RPPS_9]", "source": "regex", "category": "rpps" }, { "original": "10101856135", "replacement": "[RPPS_10]", "source": "regex", "category": "rpps" }, { "original": "10002815024", "replacement": "[RPPS_11]", "source": "regex", "category": "rpps" }, { "original": "10100817005", "replacement": "[RPPS_12]", "source": "regex", "category": "rpps" }, { "original": "10110601324", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10101096005", "replacement": "[RPPS_2]", "source": "regex", "category": "rpps" }, { "original": "10100163277", "replacement": "[RPPS_3]", "source": "regex", "category": "rpps" }, { "original": "10101639580", "replacement": "[RPPS_4]", "source": "regex", "category": "rpps" }, { "original": "10004606595", "replacement": "[RPPS_5]", "source": "regex", "category": "rpps" }, { "original": "10101480506", "replacement": "[RPPS_6]", "source": "regex", "category": "rpps" }, { "original": "10100858090", "replacement": "[RPPS_7]", "source": "regex", "category": "rpps" }, { "original": "10102268702", "replacement": "[RPPS_8]", "source": "regex", "category": "rpps" }, { "original": "10102272209", "replacement": "[RPPS_9]", "source": "regex", "category": "rpps" }, { "original": "10101856135", "replacement": "[RPPS_10]", "source": "regex", "category": "rpps" }, { "original": "10002815024", "replacement": "[RPPS_11]", "source": "regex", "category": "rpps" }, { "original": "10100817005", "replacement": "[RPPS_12]", "source": "regex", "category": "rpps" }, { "original": "10110601324", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10101096005", "replacement": "[RPPS_2]", "source": "regex", "category": "rpps" }, { "original": "10100163277", "replacement": "[RPPS_3]", "source": "regex", "category": "rpps" }, { "original": "10101639580", "replacement": "[RPPS_4]", "source": "regex", "category": "rpps" }, { "original": "10004606595", "replacement": "[RPPS_5]", "source": "regex", "category": "rpps" }, { "original": "10101480506", "replacement": "[RPPS_6]", "source": "regex", "category": "rpps" }, { "original": "10100858090", "replacement": "[RPPS_7]", "source": "regex", "category": "rpps" }, { "original": "10102268702", "replacement": "[RPPS_8]", "source": "regex", "category": "rpps" }, { "original": "10102272209", "replacement": "[RPPS_9]", "source": "regex", "category": "rpps" }, { "original": "10101856135", "replacement": "[RPPS_10]", "source": "regex", "category": "rpps" }, { "original": "10002815024", "replacement": "[RPPS_11]", "source": "regex", "category": "rpps" }, { "original": "10100817005", "replacement": "[RPPS_12]", "source": "regex", "category": "rpps" }, { "original": "10110601324", "replacement": "[RPPS_1]", "source": "regex", "category": "rpps" }, { "original": "10101096005", "replacement": "[RPPS_2]", "source": "regex", "category": "rpps" }, { "original": "10100163277", "replacement": "[RPPS_3]", "source": "regex", "category": "rpps" }, { "original": "10101639580", "replacement": "[RPPS_4]", "source": "regex", "category": "rpps" }, { "original": "10004606595", "replacement": "[RPPS_5]", "source": "regex", "category": "rpps" }, { "original": "10101480506", "replacement": "[RPPS_6]", "source": "regex", "category": "rpps" }, { "original": "10100858090", "replacement": "[RPPS_7]", "source": "regex", "category": "rpps" }, { "original": "10102268702", "replacement": "[RPPS_8]", "source": "regex", "category": "rpps" }, { "original": "10102272209", "replacement": "[RPPS_9]", "source": "regex", "category": "rpps" }, { "original": "10002815024", "replacement": "[RPPS_11]", "source": "regex", "category": "rpps" }, { "original": "10100817005", "replacement": "[RPPS_12]", "source": "regex", "category": "rpps" }, { "original": "10100858090", "replacement": "[RPPS_7]", "source": "regex", "category": "code_barre" }, { "original": "secr.medint@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "secr.medint@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "secr.medint@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "secr.medint@ch-cotebasque.fr", "replacement": "[EMAIL_1]", "source": "regex", "category": "email" }, { "original": "Dr [MEDECIN_", "replacement": "[PERSONNE_1]", "source": "ner", "score": 0.9013031721115112 }, { "original": "Stéphane MARCE", "replacement": "[MEDECIN_3]", "source": "ner", "score": 0.9959986805915833 }, { "original": "[MEDECIN", "replacement": "[PERSONNE_2]", "source": "ner", "score": 0.9695279002189636 }, { "original": "[MEDECIN_28", "replacement": "[PERSONNE_3]", "source": "ner", "score": 0.9301411509513855 }, { "original": "[MEDECIN_32", "replacement": "[PERSONNE_4]", "source": "ner", "score": 0.9407869577407837 }, { "original": "J. LOEB", "replacement": "[PERSONNE_5]", "source": "ner", "score": 0.878480851650238 }, { "original": "[MEDECIN_57", "replacement": "[PERSONNE_6]", "source": "ner", "score": 0.9403043985366821 }, { "original": "[MEDECIN_22", "replacement": "[PERSONNE_7]", "source": "ner", "score": 0.9527907967567444 }, { "original": "[MEDECIN_23", "replacement": "[PERSONNE_8]", "source": "ner", "score": 0.9620316624641418 }, { "original": "[MEDECIN_26", "replacement": "[PERSONNE_9]", "source": "ner", "score": 0.9150679707527161 }, { "original": "[MEDECIN_27", "replacement": "[PERSONNE_10]", "source": "ner", "score": 0.9694771766662598 }, { "original": "[MEDECIN_61", "replacement": "[PERSONNE_11]", "source": "ner", "score": 0.9451074600219727 }, { "original": "[MEDECIN_", "replacement": "[PERSONNE]", "source": "ner", "score": 0.9825130105018616 }, { "original": "ALEXANDRE Patrick", "replacement": "[PERSONNE_12]", "source": "ner", "score": 0.9208989143371582 } ] }