645 lines
14 KiB
JSON
645 lines
14 KiB
JSON
{
|
|
"source_file": "CRH 23176885.pdf",
|
|
"total_replacements": 318,
|
|
"regex_replacements": 219,
|
|
"ner_replacements": 8,
|
|
"sweep_replacements": 91,
|
|
"entities_found": [
|
|
{
|
|
"original": "10102326468",
|
|
"replacement": "[RPPS_1]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100422012",
|
|
"replacement": "[RPPS_2]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100673481",
|
|
"replacement": "[RPPS_3]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100402527",
|
|
"replacement": "[RPPS_4]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10002083912",
|
|
"replacement": "[RPPS_5]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10004401718",
|
|
"replacement": "[RPPS_6]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10000598366",
|
|
"replacement": "[RPPS_7]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10102326468",
|
|
"replacement": "[RPPS_1]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100422012",
|
|
"replacement": "[RPPS_2]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100673481",
|
|
"replacement": "[RPPS_3]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100402527",
|
|
"replacement": "[RPPS_4]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10002083912",
|
|
"replacement": "[RPPS_5]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10004401718",
|
|
"replacement": "[RPPS_6]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10000598366",
|
|
"replacement": "[RPPS_7]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10102326468",
|
|
"replacement": "[RPPS_1]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100422012",
|
|
"replacement": "[RPPS_2]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100673481",
|
|
"replacement": "[RPPS_3]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100402527",
|
|
"replacement": "[RPPS_4]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10002083912",
|
|
"replacement": "[RPPS_5]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10004401718",
|
|
"replacement": "[RPPS_6]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10000598366",
|
|
"replacement": "[RPPS_7]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10102326468",
|
|
"replacement": "[RPPS_1]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100422012",
|
|
"replacement": "[RPPS_2]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100673481",
|
|
"replacement": "[RPPS_3]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100402527",
|
|
"replacement": "[RPPS_4]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10002083912",
|
|
"replacement": "[RPPS_5]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10004401718",
|
|
"replacement": "[RPPS_6]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10000598366",
|
|
"replacement": "[RPPS_7]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10102326468",
|
|
"replacement": "[RPPS_1]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100422012",
|
|
"replacement": "[RPPS_2]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100673481",
|
|
"replacement": "[RPPS_3]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100402527",
|
|
"replacement": "[RPPS_4]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10002083912",
|
|
"replacement": "[RPPS_5]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10004401718",
|
|
"replacement": "[RPPS_6]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10000598366",
|
|
"replacement": "[RPPS_7]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10102326468",
|
|
"replacement": "[RPPS_1]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100422012",
|
|
"replacement": "[RPPS_2]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100673481",
|
|
"replacement": "[RPPS_3]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10100402527",
|
|
"replacement": "[RPPS_4]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10002083912",
|
|
"replacement": "[RPPS_5]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10004401718",
|
|
"replacement": "[RPPS_6]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10000598366",
|
|
"replacement": "[RPPS_7]",
|
|
"source": "regex",
|
|
"category": "rpps"
|
|
},
|
|
{
|
|
"original": "10004401716",
|
|
"replacement": "[CODE_BARRE_1]",
|
|
"source": "regex",
|
|
"category": "code_barre"
|
|
},
|
|
{
|
|
"original": "10004401716",
|
|
"replacement": "[CODE_BARRE_1]",
|
|
"source": "regex",
|
|
"category": "code_barre"
|
|
},
|
|
{
|
|
"original": "secr.csmed@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_1]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.endocrino@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_2]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "arajot@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_3]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mauzi@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_4]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mgschwind@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_5]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "emauryy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_6]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "lritz@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_7]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "ddemarsy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_8]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "sbordes-couecou@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_9]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.csmed@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_1]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.endocrino@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_2]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "arajot@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_3]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mauzi@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_4]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mgschwind@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_5]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "emauryy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_6]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "lritz@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_7]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "ddemarsy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_8]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "sbordes-couecou@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_9]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.csmed@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_1]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.endocrino@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_2]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "arajot@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_3]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mauzi@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_4]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mgschwind@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_5]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "emauryy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_6]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "lritz@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_7]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "ddemarsy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_8]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "sbordes-couecou@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_9]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.csmed@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_1]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.endocrino@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_2]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "arajot@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_3]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mauzi@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_4]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mgschwind@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_5]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "emauryy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_6]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "lritz@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_7]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "ddemarsy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_8]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "sbordes-couecou@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_9]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.csmed@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_1]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.endocrino@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_2]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "arajot@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_3]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mauzi@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_4]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mgschwind@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_5]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "emauryy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_6]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "lritz@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_7]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "ddemarsy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_8]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "sbordes-couecou@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_9]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.csmed@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_1]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "secr.endocrino@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_2]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "arajot@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_3]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mauzi@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_4]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "mgschwind@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_5]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "emauryy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_6]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "lritz@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_7]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "ddemarsy@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_8]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "sbordes-couecou@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_9]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "J. LOEB",
|
|
"replacement": "[PERSONNE_1]",
|
|
"source": "ner",
|
|
"score": 0.9530437588691711
|
|
},
|
|
{
|
|
"original": "[MEDECIN_",
|
|
"replacement": "[PERSONNE_2]",
|
|
"source": "ner",
|
|
"score": 0.9718552231788635
|
|
},
|
|
{
|
|
"original": "[MEDECIN",
|
|
"replacement": "[PERSONNE_3]",
|
|
"source": "ner",
|
|
"score": 0.9573432207107544
|
|
},
|
|
{
|
|
"original": "M.P OLAGHARRAY",
|
|
"replacement": "[PERSONNE_4]",
|
|
"source": "ner",
|
|
"score": 0.9539319276809692
|
|
},
|
|
{
|
|
"original": "[MEDECIN_23",
|
|
"replacement": "[PERSONNE_5]",
|
|
"source": "ner",
|
|
"score": 0.9381951689720154
|
|
},
|
|
{
|
|
"original": "[MEDECIN_11",
|
|
"replacement": "[PERSONNE_6]",
|
|
"source": "ner",
|
|
"score": 0.9659091830253601
|
|
},
|
|
{
|
|
"original": "VAN DE GRAAF Sven",
|
|
"replacement": "[PATIENT_2]",
|
|
"source": "ner",
|
|
"score": 0.9844681024551392
|
|
},
|
|
{
|
|
"original": "M VAN DE GRAAF",
|
|
"replacement": "[PERSONNE_7]",
|
|
"source": "ner",
|
|
"score": 0.9415469169616699
|
|
}
|
|
]
|
|
} |