{ "source_file": "CRH 23133268.pdf", "total_replacements": 249, "regex_replacements": 113, "ner_replacements": 10, "sweep_replacements": 126, "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": "10002815024", "replacement": "[RPPS_11]", "source": "regex", "category": "rpps" }, { "original": "10100817005", "replacement": "[RPPS_12]", "source": "regex", "category": "rpps" }, { "original": "10101480506", "replacement": "[RPPS_6]", "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": "[MEDECIN", "replacement": "[PERSONNE_1]", "source": "ner", "score": 0.987330436706543 }, { "original": "[MEDEC", "replacement": "[PERSONNE_2]", "source": "ner", "score": 0.9013388156890869 }, { "original": "[MEDECIN_22", "replacement": "[PERSONNE_3]", "source": "ner", "score": 0.9466954469680786 }, { "original": "[MEDECIN_36", "replacement": "[PERSONNE_4]", "source": "ner", "score": 0.936905562877655 }, { "original": "J. LOEB", "replacement": "[PERSONNE_5]", "source": "ner", "score": 0.9712404012680054 }, { "original": "Bechet", "replacement": "[PERSONNE_6]", "source": "ner", "score": 0.9415546655654907 }, { "original": "[MEDECIN_", "replacement": "[PERSONNE_7]", "source": "ner", "score": 0.9859269261360168 }, { "original": "Behçet", "replacement": "[PERSONNE_8]", "source": "ner", "score": 0.8375375270843506 }, { "original": "HLIB SABIR Luisa", "replacement": "[PERSONNE_9]", "source": "ner", "score": 0.9941368103027344 }, { "original": "[MEDECIN_41", "replacement": "[PERSONNE_10]", "source": "ner", "score": 0.9213804602622986 } ] }