675 lines
15 KiB
JSON
675 lines
15 KiB
JSON
{
|
|
"source_file": "CRH 23075530.pdf",
|
|
"total_replacements": 363,
|
|
"regex_replacements": 221,
|
|
"ner_replacements": 15,
|
|
"sweep_replacements": 127,
|
|
"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": "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": "sbordes-couecou@ch-cotebasque.fr",
|
|
"replacement": "[EMAIL_9]",
|
|
"source": "regex",
|
|
"category": "email"
|
|
},
|
|
{
|
|
"original": "[MEDECIN_",
|
|
"replacement": "[PERSONNE_1]",
|
|
"source": "ner",
|
|
"score": 0.9923322200775146
|
|
},
|
|
{
|
|
"original": "[MEDECIN_21",
|
|
"replacement": "[PERSONNE_2]",
|
|
"source": "ner",
|
|
"score": 0.9618238210678101
|
|
},
|
|
{
|
|
"original": "J. LOEB",
|
|
"replacement": "[PERSONNE_3]",
|
|
"source": "ner",
|
|
"score": 0.9681676626205444
|
|
},
|
|
{
|
|
"original": "Devaux",
|
|
"replacement": "[PERSONNE_4]",
|
|
"source": "ner",
|
|
"score": 0.9953846335411072
|
|
},
|
|
{
|
|
"original": "[MEDECIN_19",
|
|
"replacement": "[PERSONNE_5]",
|
|
"source": "ner",
|
|
"score": 0.9689444303512573
|
|
},
|
|
{
|
|
"original": "[MEDEC",
|
|
"replacement": "[PERSONNE_6]",
|
|
"source": "ner",
|
|
"score": 0.9238582849502563
|
|
},
|
|
{
|
|
"original": "[MEDECIN_18",
|
|
"replacement": "[PERSONNE_7]",
|
|
"source": "ner",
|
|
"score": 0.899200439453125
|
|
},
|
|
{
|
|
"original": "[MEDECIN_20",
|
|
"replacement": "[PERSONNE_8]",
|
|
"source": "ner",
|
|
"score": 0.8936278223991394
|
|
},
|
|
{
|
|
"original": "[MEDECIN_22",
|
|
"replacement": "[PERSONNE_9]",
|
|
"source": "ner",
|
|
"score": 0.9228649139404297
|
|
},
|
|
{
|
|
"original": "[MEDECIN",
|
|
"replacement": "[PERSONNE_10]",
|
|
"source": "ner",
|
|
"score": 0.9909365773200989
|
|
},
|
|
{
|
|
"original": "QUILLACQ",
|
|
"replacement": "[MEDECIN]",
|
|
"source": "ner",
|
|
"score": 0.8134925365447998
|
|
},
|
|
{
|
|
"original": "[MEDECIN_15",
|
|
"replacement": "[PERSONNE_11]",
|
|
"source": "ner",
|
|
"score": 0.9412944912910461
|
|
},
|
|
{
|
|
"original": "Laurence RITZ QUILLACQ",
|
|
"replacement": "[MEDECIN_18]",
|
|
"source": "ner",
|
|
"score": 0.9980672001838684
|
|
},
|
|
{
|
|
"original": "SAUQUILLO Maria",
|
|
"replacement": "[PATIENT_1]",
|
|
"source": "ner",
|
|
"score": 0.9955001473426819
|
|
},
|
|
{
|
|
"original": "[MEDECIN_39",
|
|
"replacement": "[PERSONNE_12]",
|
|
"source": "ner",
|
|
"score": 0.9722389578819275
|
|
}
|
|
]
|
|
} |