621 lines
13 KiB
JSON
621 lines
13 KiB
JSON
{
|
|
"source_file": "CRH 23106204.pdf",
|
|
"total_replacements": 467,
|
|
"regex_replacements": 227,
|
|
"ner_replacements": 20,
|
|
"sweep_replacements": 220,
|
|
"entities_found": [
|
|
{
|
|
"original": "23106204",
|
|
"replacement": "[EPISODE_1]",
|
|
"source": "regex",
|
|
"category": "episode"
|
|
},
|
|
{
|
|
"original": "23106204",
|
|
"replacement": "[EPISODE_1]",
|
|
"source": "regex",
|
|
"category": "episode"
|
|
},
|
|
{
|
|
"original": "23106204",
|
|
"replacement": "[EPISODE_1]",
|
|
"source": "regex",
|
|
"category": "episode"
|
|
},
|
|
{
|
|
"original": "23106204",
|
|
"replacement": "[EPISODE_1]",
|
|
"source": "regex",
|
|
"category": "episode"
|
|
},
|
|
{
|
|
"original": "23106204",
|
|
"replacement": "[EPISODE_1]",
|
|
"source": "regex",
|
|
"category": "episode"
|
|
},
|
|
{
|
|
"original": "23106204",
|
|
"replacement": "[EPISODE_1]",
|
|
"source": "regex",
|
|
"category": "episode"
|
|
},
|
|
{
|
|
"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": "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": "[MEDECIN_21",
|
|
"replacement": "[PERSONNE_1]",
|
|
"source": "ner",
|
|
"score": 0.9283413290977478
|
|
},
|
|
{
|
|
"original": "[MEDECIN_47",
|
|
"replacement": "[PERSONNE_2]",
|
|
"source": "ner",
|
|
"score": 0.9620317220687866
|
|
},
|
|
{
|
|
"original": "Schaeverbeke",
|
|
"replacement": "[PERSONNE_3]",
|
|
"source": "ner",
|
|
"score": 0.9976910352706909
|
|
},
|
|
{
|
|
"original": "[MEDECIN_49",
|
|
"replacement": "[PERSONNE_4]",
|
|
"source": "ner",
|
|
"score": 0.9668036699295044
|
|
},
|
|
{
|
|
"original": "[MEDECIN_51",
|
|
"replacement": "[PERSONNE_5]",
|
|
"source": "ner",
|
|
"score": 0.9826506972312927
|
|
},
|
|
{
|
|
"original": "[MEDECIN_52",
|
|
"replacement": "[PERSONNE_6]",
|
|
"source": "ner",
|
|
"score": 0.8759320378303528
|
|
},
|
|
{
|
|
"original": "Suzanne DEVAUX",
|
|
"replacement": "[MEDECIN_12]",
|
|
"source": "ner",
|
|
"score": 0.9960212111473083
|
|
},
|
|
{
|
|
"original": "[MEDEC",
|
|
"replacement": "[PERSONNE_7]",
|
|
"source": "ner",
|
|
"score": 0.9052884578704834
|
|
},
|
|
{
|
|
"original": "[MEDECIN",
|
|
"replacement": "[PERSONNE_8]",
|
|
"source": "ner",
|
|
"score": 0.9543776512145996
|
|
},
|
|
{
|
|
"original": "[MEDECIN_29",
|
|
"replacement": "[PERSONNE_9]",
|
|
"source": "ner",
|
|
"score": 0.9553312063217163
|
|
},
|
|
{
|
|
"original": "[MEDECIN_",
|
|
"replacement": "[PERSONNE_10]",
|
|
"source": "ner",
|
|
"score": 0.9908908009529114
|
|
},
|
|
{
|
|
"original": "[MEDECIN_33",
|
|
"replacement": "[PERSONNE_11]",
|
|
"source": "ner",
|
|
"score": 0.884074866771698
|
|
},
|
|
{
|
|
"original": "[MEDECIN_35",
|
|
"replacement": "[PERSONNE_12]",
|
|
"source": "ner",
|
|
"score": 0.9136056900024414
|
|
},
|
|
{
|
|
"original": "Babinski",
|
|
"replacement": "[PERSONNE_13]",
|
|
"source": "ner",
|
|
"score": 0.9957528710365295
|
|
},
|
|
{
|
|
"original": "[MEDECIN_20",
|
|
"replacement": "[PERSONNE_14]",
|
|
"source": "ner",
|
|
"score": 0.8753734230995178
|
|
},
|
|
{
|
|
"original": "[MEDECIN_48",
|
|
"replacement": "[PERSONNE_15]",
|
|
"source": "ner",
|
|
"score": 0.9527720212936401
|
|
},
|
|
{
|
|
"original": "[MEDECIN_26",
|
|
"replacement": "[PERSONNE_16]",
|
|
"source": "ner",
|
|
"score": 0.9303566813468933
|
|
},
|
|
{
|
|
"original": "[MEDECIN_50",
|
|
"replacement": "[PERSONNE_17]",
|
|
"source": "ner",
|
|
"score": 0.9252082109451294
|
|
},
|
|
{
|
|
"original": "GONZALEZ Isabelle",
|
|
"replacement": "[PERSONNE_18]",
|
|
"source": "ner",
|
|
"score": 0.9956825375556946
|
|
},
|
|
{
|
|
"original": "[MEDECIN_34",
|
|
"replacement": "[PERSONNE_19]",
|
|
"source": "ner",
|
|
"score": 0.914669930934906
|
|
}
|
|
]
|
|
} |