573 lines
12 KiB
JSON
573 lines
12 KiB
JSON
{
|
|
"source_file": "CRH 23193317.pdf",
|
|
"total_replacements": 434,
|
|
"regex_replacements": 229,
|
|
"ner_replacements": 17,
|
|
"sweep_replacements": 188,
|
|
"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": "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": "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": "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": "Itsaso ODRIOZOLA",
|
|
"replacement": "[MEDECIN_6]",
|
|
"source": "ner",
|
|
"score": 0.998072624206543
|
|
},
|
|
{
|
|
"original": "J. LOEB",
|
|
"replacement": "[PERSONNE_1]",
|
|
"source": "ner",
|
|
"score": 0.9276506304740906
|
|
},
|
|
{
|
|
"original": "[MEDECIN_35",
|
|
"replacement": "[PERSONNE_2]",
|
|
"source": "ner",
|
|
"score": 0.9107966423034668
|
|
},
|
|
{
|
|
"original": "Biermer",
|
|
"replacement": "[PERSONNE_3]",
|
|
"source": "ner",
|
|
"score": 0.9681196212768555
|
|
},
|
|
{
|
|
"original": "MEDECIN_",
|
|
"replacement": "[PERSONNE_4]",
|
|
"source": "ner",
|
|
"score": 0.8047046661376953
|
|
},
|
|
{
|
|
"original": "[MEDECIN_22",
|
|
"replacement": "[PERSONNE_5]",
|
|
"source": "ner",
|
|
"score": 0.9428607225418091
|
|
},
|
|
{
|
|
"original": "[MEDECIN_33",
|
|
"replacement": "[PERSONNE_6]",
|
|
"source": "ner",
|
|
"score": 0.9218024611473083
|
|
},
|
|
{
|
|
"original": "Thomas CLAVERIE",
|
|
"replacement": "[MEDECIN_7]",
|
|
"source": "ner",
|
|
"score": 0.9895476698875427
|
|
},
|
|
{
|
|
"original": "[MEDECIN_4",
|
|
"replacement": "[PERSONNE_7]",
|
|
"source": "ner",
|
|
"score": 0.8963046669960022
|
|
},
|
|
{
|
|
"original": "HOURDILLE Alexia",
|
|
"replacement": "[MEDECIN_17]",
|
|
"source": "ner",
|
|
"score": 0.9977534413337708
|
|
},
|
|
{
|
|
"original": "[MEDECIN_19",
|
|
"replacement": "[PERSONNE_8]",
|
|
"source": "ner",
|
|
"score": 0.9456265568733215
|
|
},
|
|
{
|
|
"original": "[MEDECIN_",
|
|
"replacement": "[PERSONNE_9]",
|
|
"source": "ner",
|
|
"score": 0.9801631569862366
|
|
},
|
|
{
|
|
"original": "[MEDECIN_53",
|
|
"replacement": "[PERSONNE_10]",
|
|
"source": "ner",
|
|
"score": 0.9320246577262878
|
|
},
|
|
{
|
|
"original": "[MEDECIN",
|
|
"replacement": "[PERSONNE_11]",
|
|
"source": "ner",
|
|
"score": 0.9897774457931519
|
|
},
|
|
{
|
|
"original": "[MEDECIN_23",
|
|
"replacement": "[PERSONNE_12]",
|
|
"source": "ner",
|
|
"score": 0.9549458622932434
|
|
},
|
|
{
|
|
"original": "[MEDECIN_65",
|
|
"replacement": "[PERSONNE_13]",
|
|
"source": "ner",
|
|
"score": 0.9409223198890686
|
|
},
|
|
{
|
|
"original": "OLHATS Auger",
|
|
"replacement": "[PERSONNE_14]",
|
|
"source": "ner",
|
|
"score": 0.9858071804046631
|
|
}
|
|
]
|
|
} |