MinhTriet commited on
Commit
6e100fb
·
verified ·
1 Parent(s): 3c7f89a

Upload folder using huggingface_hub

Browse files
ai4privacy/TokenBased-BERT/classification_report.json CHANGED
@@ -12,9 +12,9 @@
12
  "support": 107
13
  },
14
  "CITY": {
15
- "precision": 0.9901,
16
- "recall": 0.9901,
17
- "f1-score": 0.9901,
18
  "support": 203
19
  },
20
  "CREDITCARDNUMBER": {
@@ -31,8 +31,8 @@
31
  },
32
  "DRIVERLICENSENUM": {
33
  "precision": 1.0,
34
- "recall": 0.8095,
35
- "f1-score": 0.8947,
36
  "support": 21
37
  },
38
  "EMAIL": {
@@ -48,15 +48,15 @@
48
  "support": 70
49
  },
50
  "GIVENNAME": {
51
- "precision": 0.986,
52
- "recall": 0.9918,
53
- "f1-score": 0.9889,
54
  "support": 850
55
  },
56
  "IDCARDNUM": {
57
- "precision": 0.9691,
58
- "recall": 0.9592,
59
- "f1-score": 0.9641,
60
  "support": 98
61
  },
62
  "PASSPORTNUM": {
@@ -66,27 +66,27 @@
66
  "support": 41
67
  },
68
  "SOCIALNUM": {
69
- "precision": 0.9355,
70
  "recall": 1.0,
71
- "f1-score": 0.9667,
72
  "support": 29
73
  },
74
  "STREET": {
75
- "precision": 1.0,
76
- "recall": 0.9912,
77
- "f1-score": 0.9956,
78
  "support": 113
79
  },
80
  "SURNAME": {
81
- "precision": 0.9698,
82
- "recall": 0.9224,
83
- "f1-score": 0.9455,
84
  "support": 348
85
  },
86
  "TAXNUM": {
87
  "precision": 1.0,
88
- "recall": 1.0,
89
- "f1-score": 1.0,
90
  "support": 24
91
  },
92
  "TELEPHONENUM": {
@@ -102,9 +102,9 @@
102
  "support": 144
103
  },
104
  "TITLE": {
105
- "precision": 1.0,
106
- "recall": 1.0,
107
- "f1-score": 1.0,
108
  "support": 119
109
  },
110
  "ZIPCODE": {
@@ -114,21 +114,21 @@
114
  "support": 51
115
  },
116
  "OVERALL_MICRO": {
117
- "precision": 0.9856,
118
- "recall": 0.9816,
119
- "f1-score": 0.9836,
120
  "support": 2723
121
  },
122
  "OVERALL_MACRO": {
123
- "precision": 0.984,
124
- "recall": 0.9791,
125
- "f1-score": 0.9808,
126
  "support": 2723
127
  },
128
  "OVERALL_WEIGHTED": {
129
- "precision": 0.9856,
130
- "recall": 0.9816,
131
- "f1-score": 0.9834,
132
  "support": 2723
133
  }
134
  }
 
12
  "support": 107
13
  },
14
  "CITY": {
15
+ "precision": 0.9852,
16
+ "recall": 0.9852,
17
+ "f1-score": 0.9852,
18
  "support": 203
19
  },
20
  "CREDITCARDNUMBER": {
 
31
  },
32
  "DRIVERLICENSENUM": {
33
  "precision": 1.0,
34
+ "recall": 0.7143,
35
+ "f1-score": 0.8333,
36
  "support": 21
37
  },
38
  "EMAIL": {
 
48
  "support": 70
49
  },
50
  "GIVENNAME": {
51
+ "precision": 0.9791,
52
+ "recall": 0.9929,
53
+ "f1-score": 0.986,
54
  "support": 850
55
  },
56
  "IDCARDNUM": {
57
+ "precision": 0.9596,
58
+ "recall": 0.9694,
59
+ "f1-score": 0.9645,
60
  "support": 98
61
  },
62
  "PASSPORTNUM": {
 
66
  "support": 41
67
  },
68
  "SOCIALNUM": {
69
+ "precision": 0.8286,
70
  "recall": 1.0,
71
+ "f1-score": 0.9062,
72
  "support": 29
73
  },
74
  "STREET": {
75
+ "precision": 0.9911,
76
+ "recall": 0.9823,
77
+ "f1-score": 0.9867,
78
  "support": 113
79
  },
80
  "SURNAME": {
81
+ "precision": 0.952,
82
+ "recall": 0.9109,
83
+ "f1-score": 0.931,
84
  "support": 348
85
  },
86
  "TAXNUM": {
87
  "precision": 1.0,
88
+ "recall": 0.8333,
89
+ "f1-score": 0.9091,
90
  "support": 24
91
  },
92
  "TELEPHONENUM": {
 
102
  "support": 144
103
  },
104
  "TITLE": {
105
+ "precision": 0.9916,
106
+ "recall": 0.9916,
107
+ "f1-score": 0.9916,
108
  "support": 119
109
  },
110
  "ZIPCODE": {
 
114
  "support": 51
115
  },
116
  "OVERALL_MICRO": {
117
+ "precision": 0.9783,
118
+ "recall": 0.9776,
119
+ "f1-score": 0.978,
120
  "support": 2723
121
  },
122
  "OVERALL_MACRO": {
123
+ "precision": 0.9754,
124
+ "recall": 0.9641,
125
+ "f1-score": 0.9676,
126
  "support": 2723
127
  },
128
  "OVERALL_WEIGHTED": {
129
+ "precision": 0.9786,
130
+ "recall": 0.9776,
131
+ "f1-score": 0.9777,
132
  "support": 2723
133
  }
134
  }
ai4privacy/TokenBased-BERT/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cedf035bdc1f395924be6a84c9b085414dab8f55af3f6073e9c406fe6359a82
3
  size 435709876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33b8f80602332338edea50563cb4eb3f2749b1be93d8d1cf5f0208fbc7b4ea41
3
  size 435709876
ai4privacy/TokenBased-BERT/predictions.json CHANGED
@@ -17,7 +17,7 @@
17
  ],
18
  "predictions": [
19
  {
20
- "tag": "SURNAME",
21
  "start": 0,
22
  "end": 7,
23
  "value": "Erbagan"
@@ -616,7 +616,7 @@
616
  "value": "NZ6255728"
617
  },
618
  {
619
- "tag": "IDCARDNUM",
620
  "start": 101,
621
  "end": 111,
622
  "value": "5BT3C9WWQA"
@@ -2218,8 +2218,8 @@
2218
  {
2219
  "tag": "GIVENNAME",
2220
  "start": 0,
2221
- "end": 12,
2222
- "value": "Efraïm Caran"
2223
  },
2224
  {
2225
  "tag": "TITLE",
@@ -2570,10 +2570,10 @@
2570
  "value": "Chayanne"
2571
  },
2572
  {
2573
- "tag": "GIVENNAME",
2574
  "start": 105,
2575
- "end": 115,
2576
- "value": "Sivalogini"
2577
  }
2578
  ]
2579
  },
@@ -3187,14 +3187,14 @@
3187
  {
3188
  "tag": "GIVENNAME",
3189
  "start": 15,
3190
- "end": 21,
3191
- "value": "Ibraim"
3192
  },
3193
  {
3194
  "tag": "SURNAME",
3195
- "start": 22,
3196
  "end": 43,
3197
- "value": "Amarasingha Käshammer"
3198
  },
3199
  {
3200
  "tag": "ZIPCODE",
@@ -3781,7 +3781,7 @@
3781
  "value": "Madame"
3782
  },
3783
  {
3784
- "tag": "GIVENNAME",
3785
  "start": 7,
3786
  "end": 14,
3787
  "value": "Socrate"
@@ -3832,14 +3832,8 @@
3832
  {
3833
  "tag": "GIVENNAME",
3834
  "start": 87,
3835
- "end": 92,
3836
- "value": "Sejan"
3837
- },
3838
- {
3839
- "tag": "SURNAME",
3840
- "start": 93,
3841
- "end": 97,
3842
- "value": "Gnat"
3843
  }
3844
  ]
3845
  },
@@ -4813,10 +4807,10 @@
4813
  "value": "Mengying"
4814
  },
4815
  {
4816
- "tag": "SURNAME",
4817
  "start": 44,
4818
- "end": 46,
4819
- "value": "Ol"
4820
  },
4821
  {
4822
  "tag": "SURNAME",
@@ -5347,12 +5341,6 @@
5347
  "start": 0,
5348
  "end": 16,
5349
  "value": "Kassiani Serveta"
5350
- },
5351
- {
5352
- "tag": "SURNAME",
5353
- "start": 17,
5354
- "end": 36,
5355
- "value": "Ajith Sonnentrücker"
5356
  }
5357
  ]
5358
  },
@@ -5394,8 +5382,8 @@
5394
  {
5395
  "tag": "GIVENNAME",
5396
  "start": 77,
5397
- "end": 90,
5398
- "value": "Dionisa Magbu"
5399
  }
5400
  ]
5401
  },
@@ -6119,8 +6107,8 @@
6119
  {
6120
  "tag": "SURNAME",
6121
  "start": 63,
6122
- "end": 70,
6123
- "value": "Insolia"
6124
  }
6125
  ]
6126
  },
@@ -6921,8 +6909,14 @@
6921
  {
6922
  "tag": "GIVENNAME",
6923
  "start": 27,
 
 
 
 
 
 
6924
  "end": 42,
6925
- "value": "Loghman Marsell"
6926
  }
6927
  ]
6928
  },
@@ -7587,8 +7581,8 @@
7587
  {
7588
  "tag": "GIVENNAME",
7589
  "start": 141,
7590
- "end": 148,
7591
- "value": "Nessrin"
7592
  },
7593
  {
7594
  "tag": "DATE",
@@ -7753,8 +7747,14 @@
7753
  {
7754
  "tag": "GIVENNAME",
7755
  "start": 46,
 
 
 
 
 
 
7756
  "end": 61,
7757
- "value": "Zijavere Dorjee"
7758
  }
7759
  ]
7760
  },
@@ -9558,14 +9558,8 @@
9558
  {
9559
  "tag": "GIVENNAME",
9560
  "start": 11,
9561
- "end": 17,
9562
- "value": "Ramany"
9563
- },
9564
- {
9565
- "tag": "SURNAME",
9566
- "start": 18,
9567
  "end": 20,
9568
- "value": "Va"
9569
  }
9570
  ]
9571
  },
@@ -9605,7 +9599,7 @@
9605
  ],
9606
  "predictions": [
9607
  {
9608
- "tag": "TITLE",
9609
  "start": 45,
9610
  "end": 48,
9611
  "value": "Del"
@@ -10698,14 +10692,8 @@
10698
  {
10699
  "tag": "GIVENNAME",
10700
  "start": 5,
10701
- "end": 9,
10702
- "value": "Ezra"
10703
- },
10704
- {
10705
- "tag": "SURNAME",
10706
- "start": 10,
10707
- "end": 18,
10708
- "value": "Marcelos"
10709
  }
10710
  ]
10711
  },
@@ -12008,8 +11996,8 @@
12008
  {
12009
  "tag": "GIVENNAME",
12010
  "start": 64,
12011
- "end": 71,
12012
- "value": "Lumturi"
12013
  }
12014
  ]
12015
  },
@@ -12187,8 +12175,14 @@
12187
  {
12188
  "tag": "GIVENNAME",
12189
  "start": 0,
 
 
 
 
 
 
12190
  "end": 12,
12191
- "value": "Lory Schekeb"
12192
  }
12193
  ]
12194
  },
@@ -14128,14 +14122,14 @@
14128
  {
14129
  "tag": "GIVENNAME",
14130
  "start": 11,
14131
- "end": 22,
14132
- "value": "Mitzy Gorda"
14133
  },
14134
  {
14135
  "tag": "SURNAME",
14136
- "start": 23,
14137
  "end": 31,
14138
- "value": "Sulandra"
14139
  }
14140
  ]
14141
  },
@@ -14430,8 +14424,14 @@
14430
  {
14431
  "tag": "GIVENNAME",
14432
  "start": 112,
14433
- "end": 126,
14434
- "value": "Yanet Vukosava"
 
 
 
 
 
 
14435
  },
14436
  {
14437
  "tag": "SURNAME",
@@ -14465,10 +14465,10 @@
14465
  ],
14466
  "predictions": [
14467
  {
14468
- "tag": "SOCIALNUM",
14469
  "start": 95,
14470
- "end": 105,
14471
- "value": "1839904108"
14472
  }
14473
  ]
14474
  },
@@ -14850,14 +14850,14 @@
14850
  {
14851
  "tag": "GIVENNAME",
14852
  "start": 6,
14853
- "end": 18,
14854
- "value": "Albim Celebi"
14855
  },
14856
  {
14857
  "tag": "SURNAME",
14858
- "start": 19,
14859
- "end": 31,
14860
- "value": "Eusebio Love"
14861
  }
14862
  ]
14863
  },
@@ -15290,14 +15290,8 @@
15290
  {
15291
  "tag": "GIVENNAME",
15292
  "start": 0,
15293
- "end": 8,
15294
- "value": "Giselène"
15295
- },
15296
- {
15297
- "tag": "SURNAME",
15298
- "start": 9,
15299
- "end": 14,
15300
- "value": "Süsli"
15301
  },
15302
  {
15303
  "tag": "TITLE",
@@ -15816,8 +15810,8 @@
15816
  {
15817
  "tag": "GIVENNAME",
15818
  "start": 29,
15819
- "end": 45,
15820
- "value": "Istvanne Cmiljka"
15821
  },
15822
  {
15823
  "tag": "CITY",
@@ -15893,7 +15887,7 @@
15893
  "value": "Calgary"
15894
  },
15895
  {
15896
- "tag": "DRIVERLICENSENUM",
15897
  "start": 81,
15898
  "end": 91,
15899
  "value": "IW5VO4QPLM"
@@ -16288,8 +16282,14 @@
16288
  {
16289
  "tag": "GIVENNAME",
16290
  "start": 41,
16291
- "end": 51,
16292
- "value": "Léonce Rey"
 
 
 
 
 
 
16293
  }
16294
  ]
16295
  },
@@ -17432,6 +17432,12 @@
17432
  "start": 0,
17433
  "end": 6,
17434
  "value": "Mister"
 
 
 
 
 
 
17435
  }
17436
  ]
17437
  },
@@ -18569,8 +18575,14 @@
18569
  {
18570
  "tag": "GIVENNAME",
18571
  "start": 37,
 
 
 
 
 
 
18572
  "end": 51,
18573
- "value": "Rahimeh Henjes"
18574
  }
18575
  ]
18576
  },
@@ -19273,12 +19285,6 @@
19273
  "end": 71,
19274
  "value": "Grand-Remous"
19275
  },
19276
- {
19277
- "tag": "STREET",
19278
- "start": 72,
19279
- "end": 87,
19280
- "value": "John Folke Road"
19281
- },
19282
  {
19283
  "tag": "BUILDINGNUM",
19284
  "start": 88,
@@ -19595,8 +19601,14 @@
19595
  {
19596
  "tag": "SURNAME",
19597
  "start": 4,
 
 
 
 
 
 
19598
  "end": 19,
19599
- "value": "Alpay Akbarpour"
19600
  },
19601
  {
19602
  "tag": "TITLE",
@@ -20903,7 +20915,7 @@
20903
  "value": "13564.48503"
20904
  },
20905
  {
20906
- "tag": "PASSPORTNUM",
20907
  "start": 246,
20908
  "end": 255,
20909
  "value": "632320697"
@@ -21546,7 +21558,7 @@
21546
  "value": "087-51-6641"
21547
  },
21548
  {
21549
- "tag": "DRIVERLICENSENUM",
21550
  "start": 84,
21551
  "end": 92,
21552
  "value": "30451213"
@@ -21622,8 +21634,8 @@
21622
  {
21623
  "tag": "CITY",
21624
  "start": 49,
21625
- "end": 58,
21626
- "value": "Groveport"
21627
  },
21628
  {
21629
  "tag": "EMAIL",
@@ -21671,8 +21683,14 @@
21671
  {
21672
  "tag": "GIVENNAME",
21673
  "start": 90,
 
 
 
 
 
 
21674
  "end": 101,
21675
- "value": "Munir Baset"
21676
  },
21677
  {
21678
  "tag": "STREET",
@@ -22599,14 +22617,8 @@
22599
  {
22600
  "tag": "GIVENNAME",
22601
  "start": 39,
22602
- "end": 44,
22603
- "value": "Jenoe"
22604
- },
22605
- {
22606
- "tag": "SURNAME",
22607
- "start": 45,
22608
- "end": 51,
22609
- "value": "Maziad"
22610
  },
22611
  {
22612
  "tag": "DATE",
@@ -23413,6 +23425,12 @@
23413
  }
23414
  ],
23415
  "predictions": [
 
 
 
 
 
 
23416
  {
23417
  "tag": "BUILDINGNUM",
23418
  "start": 8,
@@ -23783,8 +23801,8 @@
23783
  {
23784
  "tag": "GIVENNAME",
23785
  "start": 23,
23786
- "end": 39,
23787
- "value": "Brooklyn Casiano"
23788
  },
23789
  {
23790
  "tag": "CITY",
@@ -23973,8 +23991,8 @@
23973
  {
23974
  "tag": "GIVENNAME",
23975
  "start": 20,
23976
- "end": 33,
23977
- "value": "Saïa Rongfang"
23978
  },
23979
  {
23980
  "tag": "CITY",
@@ -24317,8 +24335,14 @@
24317
  {
24318
  "tag": "GIVENNAME",
24319
  "start": 528,
 
 
 
 
 
 
24320
  "end": 540,
24321
- "value": "Fady Willame"
24322
  },
24323
  {
24324
  "tag": "BUILDINGNUM",
@@ -24893,8 +24917,14 @@
24893
  {
24894
  "tag": "GIVENNAME",
24895
  "start": 7,
24896
- "end": 15,
24897
- "value": "Kereka G"
 
 
 
 
 
 
24898
  },
24899
  {
24900
  "tag": "CITY",
@@ -25736,8 +25766,14 @@
25736
  {
25737
  "tag": "GIVENNAME",
25738
  "start": 0,
 
 
 
 
 
 
25739
  "end": 20,
25740
- "value": "Pierre-Laurent Walas"
25741
  },
25742
  {
25743
  "tag": "AGE",
@@ -26777,7 +26813,7 @@
26777
  "value": "Subagini"
26778
  },
26779
  {
26780
- "tag": "SURNAME",
26781
  "start": 44,
26782
  "end": 49,
26783
  "value": "Jakow"
@@ -27164,10 +27200,10 @@
27164
  ],
27165
  "predictions": [
27166
  {
27167
- "tag": "SURNAME",
27168
  "start": 8,
27169
- "end": 17,
27170
- "value": "Liselotti"
27171
  },
27172
  {
27173
  "tag": "CREDITCARDNUMBER",
@@ -27268,10 +27304,10 @@
27268
  "value": "Cormorèche"
27269
  },
27270
  {
27271
- "tag": "TAXNUM",
27272
  "start": 37,
27273
- "end": 41,
27274
- "value": "1784"
27275
  },
27276
  {
27277
  "tag": "SOCIALNUM",
@@ -28271,7 +28307,7 @@
28271
  "value": "Thargini"
28272
  },
28273
  {
28274
- "tag": "SURNAME",
28275
  "start": 57,
28276
  "end": 63,
28277
  "value": "Bugnon"
@@ -29121,8 +29157,8 @@
29121
  {
29122
  "tag": "CITY",
29123
  "start": 118,
29124
- "end": 134,
29125
- "value": "York City Centre"
29126
  }
29127
  ]
29128
  },
@@ -29649,10 +29685,16 @@
29649
  ],
29650
  "predictions": [
29651
  {
29652
- "tag": "SURNAME",
29653
  "start": 0,
 
 
 
 
 
 
29654
  "end": 25,
29655
- "value": "Zufferey Gutenhan Morella"
29656
  }
29657
  ]
29658
  },
@@ -29803,10 +29845,10 @@
29803
  "value": "Glencairn"
29804
  },
29805
  {
29806
- "tag": "TAXNUM",
29807
  "start": 90,
29808
- "end": 94,
29809
- "value": "1653"
29810
  },
29811
  {
29812
  "tag": "PASSPORTNUM",
@@ -29916,8 +29958,14 @@
29916
  {
29917
  "tag": "GIVENNAME",
29918
  "start": 0,
29919
- "end": 7,
29920
- "value": "Gora Ts"
 
 
 
 
 
 
29921
  },
29922
  {
29923
  "tag": "EMAIL",
@@ -30832,8 +30880,14 @@
30832
  {
30833
  "tag": "GIVENNAME",
30834
  "start": 49,
 
 
 
 
 
 
30835
  "end": 63,
30836
- "value": "Lawrence Vicko"
30837
  },
30838
  {
30839
  "tag": "EMAIL",
@@ -31219,14 +31273,8 @@
31219
  {
31220
  "tag": "GIVENNAME",
31221
  "start": 27,
31222
- "end": 36,
31223
- "value": "Rajwinder"
31224
- },
31225
- {
31226
- "tag": "SURNAME",
31227
- "start": 37,
31228
- "end": 44,
31229
- "value": "Gimonet"
31230
  },
31231
  {
31232
  "tag": "IDCARDNUM",
@@ -31273,7 +31321,7 @@
31273
  ],
31274
  "predictions": [
31275
  {
31276
- "tag": "TAXNUM",
31277
  "start": 47,
31278
  "end": 57,
31279
  "value": "0756957395"
@@ -31614,8 +31662,8 @@
31614
  {
31615
  "tag": "GIVENNAME",
31616
  "start": 34,
31617
- "end": 46,
31618
- "value": "Prerana Miño"
31619
  },
31620
  {
31621
  "tag": "GIVENNAME",
@@ -31913,10 +31961,10 @@
31913
  "value": "Shkljzen"
31914
  },
31915
  {
31916
- "tag": "DRIVERLICENSENUM",
31917
  "start": 58,
31918
- "end": 62,
31919
- "value": "4KIE"
31920
  }
31921
  ]
31922
  },
@@ -33077,8 +33125,8 @@
33077
  {
33078
  "tag": "TAXNUM",
33079
  "start": 129,
33080
- "end": 139,
33081
- "value": "5632435501"
33082
  }
33083
  ]
33084
  },
@@ -33545,8 +33593,8 @@
33545
  {
33546
  "tag": "SURNAME",
33547
  "start": 43,
33548
- "end": 50,
33549
- "value": "Douspis"
33550
  },
33551
  {
33552
  "tag": "EMAIL",
@@ -33851,10 +33899,10 @@
33851
  ],
33852
  "predictions": [
33853
  {
33854
- "tag": "TAXNUM",
33855
  "start": 20,
33856
- "end": 30,
33857
- "value": "0902009013"
33858
  }
33859
  ]
33860
  },
@@ -34091,7 +34139,7 @@
34091
  "value": "Vannia Serafettin"
34092
  },
34093
  {
34094
- "tag": "CITY",
34095
  "start": 71,
34096
  "end": 77,
34097
  "value": "Colusa"
@@ -34540,8 +34588,8 @@
34540
  {
34541
  "tag": "GIVENNAME",
34542
  "start": 90,
34543
- "end": 104,
34544
- "value": "Dastan Gonçala"
34545
  },
34546
  {
34547
  "tag": "CITY",
@@ -34756,8 +34804,8 @@
34756
  {
34757
  "tag": "GIVENNAME",
34758
  "start": 28,
34759
- "end": 33,
34760
- "value": "Warin"
34761
  }
34762
  ]
34763
  },
@@ -35568,8 +35616,14 @@
35568
  {
35569
  "tag": "GIVENNAME",
35570
  "start": 16,
 
 
 
 
 
 
35571
  "end": 29,
35572
- "value": "Mayram Janiel"
35573
  },
35574
  {
35575
  "tag": "DATE",
@@ -37231,7 +37285,7 @@
37231
  "value": "Muraleetharan Balraj"
37232
  },
37233
  {
37234
- "tag": "SURNAME",
37235
  "start": 139,
37236
  "end": 145,
37237
  "value": "Jeevan"
@@ -38358,8 +38412,8 @@
38358
  {
38359
  "tag": "CITY",
38360
  "start": 93,
38361
- "end": 97,
38362
- "value": "Fair"
38363
  }
38364
  ]
38365
  },
 
17
  ],
18
  "predictions": [
19
  {
20
+ "tag": "GIVENNAME",
21
  "start": 0,
22
  "end": 7,
23
  "value": "Erbagan"
 
616
  "value": "NZ6255728"
617
  },
618
  {
619
+ "tag": "DRIVERLICENSENUM",
620
  "start": 101,
621
  "end": 111,
622
  "value": "5BT3C9WWQA"
 
2218
  {
2219
  "tag": "GIVENNAME",
2220
  "start": 0,
2221
+ "end": 11,
2222
+ "value": "Efraïm Cara"
2223
  },
2224
  {
2225
  "tag": "TITLE",
 
2570
  "value": "Chayanne"
2571
  },
2572
  {
2573
+ "tag": "CITY",
2574
  "start": 105,
2575
+ "end": 107,
2576
+ "value": "Si"
2577
  }
2578
  ]
2579
  },
 
3187
  {
3188
  "tag": "GIVENNAME",
3189
  "start": 15,
3190
+ "end": 27,
3191
+ "value": "Ibraim Amara"
3192
  },
3193
  {
3194
  "tag": "SURNAME",
3195
+ "start": 34,
3196
  "end": 43,
3197
+ "value": "Käshammer"
3198
  },
3199
  {
3200
  "tag": "ZIPCODE",
 
3781
  "value": "Madame"
3782
  },
3783
  {
3784
+ "tag": "SURNAME",
3785
  "start": 7,
3786
  "end": 14,
3787
  "value": "Socrate"
 
3832
  {
3833
  "tag": "GIVENNAME",
3834
  "start": 87,
3835
+ "end": 94,
3836
+ "value": "Sejan G"
 
 
 
 
 
 
3837
  }
3838
  ]
3839
  },
 
4807
  "value": "Mengying"
4808
  },
4809
  {
4810
+ "tag": "GIVENNAME",
4811
  "start": 44,
4812
+ "end": 50,
4813
+ "value": "Olguta"
4814
  },
4815
  {
4816
  "tag": "SURNAME",
 
5341
  "start": 0,
5342
  "end": 16,
5343
  "value": "Kassiani Serveta"
 
 
 
 
 
 
5344
  }
5345
  ]
5346
  },
 
5382
  {
5383
  "tag": "GIVENNAME",
5384
  "start": 77,
5385
+ "end": 88,
5386
+ "value": "Dionisa Mag"
5387
  }
5388
  ]
5389
  },
 
6107
  {
6108
  "tag": "SURNAME",
6109
  "start": 63,
6110
+ "end": 69,
6111
+ "value": "Insoli"
6112
  }
6113
  ]
6114
  },
 
6909
  {
6910
  "tag": "GIVENNAME",
6911
  "start": 27,
6912
+ "end": 34,
6913
+ "value": "Loghman"
6914
+ },
6915
+ {
6916
+ "tag": "SURNAME",
6917
+ "start": 35,
6918
  "end": 42,
6919
+ "value": "Marsell"
6920
  }
6921
  ]
6922
  },
 
7581
  {
7582
  "tag": "GIVENNAME",
7583
  "start": 141,
7584
+ "end": 145,
7585
+ "value": "Ness"
7586
  },
7587
  {
7588
  "tag": "DATE",
 
7747
  {
7748
  "tag": "GIVENNAME",
7749
  "start": 46,
7750
+ "end": 54,
7751
+ "value": "Zijavere"
7752
+ },
7753
+ {
7754
+ "tag": "SURNAME",
7755
+ "start": 55,
7756
  "end": 61,
7757
+ "value": "Dorjee"
7758
  }
7759
  ]
7760
  },
 
9558
  {
9559
  "tag": "GIVENNAME",
9560
  "start": 11,
 
 
 
 
 
 
9561
  "end": 20,
9562
+ "value": "Ramany Va"
9563
  }
9564
  ]
9565
  },
 
9599
  ],
9600
  "predictions": [
9601
  {
9602
+ "tag": "GIVENNAME",
9603
  "start": 45,
9604
  "end": 48,
9605
  "value": "Del"
 
10692
  {
10693
  "tag": "GIVENNAME",
10694
  "start": 5,
10695
+ "end": 17,
10696
+ "value": "Ezra Marcelo"
 
 
 
 
 
 
10697
  }
10698
  ]
10699
  },
 
11996
  {
11997
  "tag": "GIVENNAME",
11998
  "start": 64,
11999
+ "end": 66,
12000
+ "value": "Lu"
12001
  }
12002
  ]
12003
  },
 
12175
  {
12176
  "tag": "GIVENNAME",
12177
  "start": 0,
12178
+ "end": 4,
12179
+ "value": "Lory"
12180
+ },
12181
+ {
12182
+ "tag": "SURNAME",
12183
+ "start": 5,
12184
  "end": 12,
12185
+ "value": "Schekeb"
12186
  }
12187
  ]
12188
  },
 
14122
  {
14123
  "tag": "GIVENNAME",
14124
  "start": 11,
14125
+ "end": 16,
14126
+ "value": "Mitzy"
14127
  },
14128
  {
14129
  "tag": "SURNAME",
14130
+ "start": 17,
14131
  "end": 31,
14132
+ "value": "Gorda Sulandra"
14133
  }
14134
  ]
14135
  },
 
14424
  {
14425
  "tag": "GIVENNAME",
14426
  "start": 112,
14427
+ "end": 117,
14428
+ "value": "Yanet"
14429
+ },
14430
+ {
14431
+ "tag": "SURNAME",
14432
+ "start": 118,
14433
+ "end": 120,
14434
+ "value": "Vu"
14435
  },
14436
  {
14437
  "tag": "SURNAME",
 
14465
  ],
14466
  "predictions": [
14467
  {
14468
+ "tag": "IDCARDNUM",
14469
  "start": 95,
14470
+ "end": 99,
14471
+ "value": "1839"
14472
  }
14473
  ]
14474
  },
 
14850
  {
14851
  "tag": "GIVENNAME",
14852
  "start": 6,
14853
+ "end": 11,
14854
+ "value": "Albim"
14855
  },
14856
  {
14857
  "tag": "SURNAME",
14858
+ "start": 12,
14859
+ "end": 14,
14860
+ "value": "Ce"
14861
  }
14862
  ]
14863
  },
 
15290
  {
15291
  "tag": "GIVENNAME",
15292
  "start": 0,
15293
+ "end": 11,
15294
+ "value": "Giselène Sü"
 
 
 
 
 
 
15295
  },
15296
  {
15297
  "tag": "TITLE",
 
15810
  {
15811
  "tag": "GIVENNAME",
15812
  "start": 29,
15813
+ "end": 40,
15814
+ "value": "Istvanne Cm"
15815
  },
15816
  {
15817
  "tag": "CITY",
 
15887
  "value": "Calgary"
15888
  },
15889
  {
15890
+ "tag": "IDCARDNUM",
15891
  "start": 81,
15892
  "end": 91,
15893
  "value": "IW5VO4QPLM"
 
16282
  {
16283
  "tag": "GIVENNAME",
16284
  "start": 41,
16285
+ "end": 47,
16286
+ "value": "Léonce"
16287
+ },
16288
+ {
16289
+ "tag": "SURNAME",
16290
+ "start": 48,
16291
+ "end": 53,
16292
+ "value": "Reyeg"
16293
  }
16294
  ]
16295
  },
 
17432
  "start": 0,
17433
  "end": 6,
17434
  "value": "Mister"
17435
+ },
17436
+ {
17437
+ "tag": "TITLE",
17438
+ "start": 34,
17439
+ "end": 37,
17440
+ "value": "ENG"
17441
  }
17442
  ]
17443
  },
 
18575
  {
18576
  "tag": "GIVENNAME",
18577
  "start": 37,
18578
+ "end": 44,
18579
+ "value": "Rahimeh"
18580
+ },
18581
+ {
18582
+ "tag": "SURNAME",
18583
+ "start": 45,
18584
  "end": 51,
18585
+ "value": "Henjes"
18586
  }
18587
  ]
18588
  },
 
19285
  "end": 71,
19286
  "value": "Grand-Remous"
19287
  },
 
 
 
 
 
 
19288
  {
19289
  "tag": "BUILDINGNUM",
19290
  "start": 88,
 
19601
  {
19602
  "tag": "SURNAME",
19603
  "start": 4,
19604
+ "end": 9,
19605
+ "value": "Alpay"
19606
+ },
19607
+ {
19608
+ "tag": "SURNAME",
19609
+ "start": 10,
19610
  "end": 19,
19611
+ "value": "Akbarpour"
19612
  },
19613
  {
19614
  "tag": "TITLE",
 
20915
  "value": "13564.48503"
20916
  },
20917
  {
20918
+ "tag": "SOCIALNUM",
20919
  "start": 246,
20920
  "end": 255,
20921
  "value": "632320697"
 
21558
  "value": "087-51-6641"
21559
  },
21560
  {
21561
+ "tag": "PASSPORTNUM",
21562
  "start": 84,
21563
  "end": 92,
21564
  "value": "30451213"
 
21634
  {
21635
  "tag": "CITY",
21636
  "start": 49,
21637
+ "end": 68,
21638
+ "value": "GroveportxPemberton"
21639
  },
21640
  {
21641
  "tag": "EMAIL",
 
21683
  {
21684
  "tag": "GIVENNAME",
21685
  "start": 90,
21686
+ "end": 95,
21687
+ "value": "Munir"
21688
+ },
21689
+ {
21690
+ "tag": "SURNAME",
21691
+ "start": 96,
21692
  "end": 101,
21693
+ "value": "Baset"
21694
  },
21695
  {
21696
  "tag": "STREET",
 
22617
  {
22618
  "tag": "GIVENNAME",
22619
  "start": 39,
22620
+ "end": 50,
22621
+ "value": "Jenoe Mazia"
 
 
 
 
 
 
22622
  },
22623
  {
22624
  "tag": "DATE",
 
23425
  }
23426
  ],
23427
  "predictions": [
23428
+ {
23429
+ "tag": "STREET",
23430
+ "start": 0,
23431
+ "end": 7,
23432
+ "value": "Railway"
23433
+ },
23434
  {
23435
  "tag": "BUILDINGNUM",
23436
  "start": 8,
 
23801
  {
23802
  "tag": "GIVENNAME",
23803
  "start": 23,
23804
+ "end": 35,
23805
+ "value": "Brooklyn Cas"
23806
  },
23807
  {
23808
  "tag": "CITY",
 
23991
  {
23992
  "tag": "GIVENNAME",
23993
  "start": 20,
23994
+ "end": 28,
23995
+ "value": "Saïa Ron"
23996
  },
23997
  {
23998
  "tag": "CITY",
 
24335
  {
24336
  "tag": "GIVENNAME",
24337
  "start": 528,
24338
+ "end": 532,
24339
+ "value": "Fady"
24340
+ },
24341
+ {
24342
+ "tag": "SURNAME",
24343
+ "start": 533,
24344
  "end": 540,
24345
+ "value": "Willame"
24346
  },
24347
  {
24348
  "tag": "BUILDINGNUM",
 
24917
  {
24918
  "tag": "GIVENNAME",
24919
  "start": 7,
24920
+ "end": 13,
24921
+ "value": "Kereka"
24922
+ },
24923
+ {
24924
+ "tag": "SURNAME",
24925
+ "start": 14,
24926
+ "end": 20,
24927
+ "value": "Ghersa"
24928
  },
24929
  {
24930
  "tag": "CITY",
 
25766
  {
25767
  "tag": "GIVENNAME",
25768
  "start": 0,
25769
+ "end": 14,
25770
+ "value": "Pierre-Laurent"
25771
+ },
25772
+ {
25773
+ "tag": "SURNAME",
25774
+ "start": 15,
25775
  "end": 20,
25776
+ "value": "Walas"
25777
  },
25778
  {
25779
  "tag": "AGE",
 
26813
  "value": "Subagini"
26814
  },
26815
  {
26816
+ "tag": "GIVENNAME",
26817
  "start": 44,
26818
  "end": 49,
26819
  "value": "Jakow"
 
27200
  ],
27201
  "predictions": [
27202
  {
27203
+ "tag": "GIVENNAME",
27204
  "start": 8,
27205
+ "end": 22,
27206
+ "value": "Liselotti Alie"
27207
  },
27208
  {
27209
  "tag": "CREDITCARDNUMBER",
 
27304
  "value": "Cormorèche"
27305
  },
27306
  {
27307
+ "tag": "SOCIALNUM",
27308
  "start": 37,
27309
+ "end": 47,
27310
+ "value": "1784327053"
27311
  },
27312
  {
27313
  "tag": "SOCIALNUM",
 
28307
  "value": "Thargini"
28308
  },
28309
  {
28310
+ "tag": "GIVENNAME",
28311
  "start": 57,
28312
  "end": 63,
28313
  "value": "Bugnon"
 
29157
  {
29158
  "tag": "CITY",
29159
  "start": 118,
29160
+ "end": 122,
29161
+ "value": "York"
29162
  }
29163
  ]
29164
  },
 
29685
  ],
29686
  "predictions": [
29687
  {
29688
+ "tag": "GIVENNAME",
29689
  "start": 0,
29690
+ "end": 8,
29691
+ "value": "Zufferey"
29692
+ },
29693
+ {
29694
+ "tag": "SURNAME",
29695
+ "start": 9,
29696
  "end": 25,
29697
+ "value": "Gutenhan Morella"
29698
  }
29699
  ]
29700
  },
 
29845
  "value": "Glencairn"
29846
  },
29847
  {
29848
+ "tag": "SOCIALNUM",
29849
  "start": 90,
29850
+ "end": 100,
29851
+ "value": "1653144036"
29852
  },
29853
  {
29854
  "tag": "PASSPORTNUM",
 
29958
  {
29959
  "tag": "GIVENNAME",
29960
  "start": 0,
29961
+ "end": 4,
29962
+ "value": "Gora"
29963
+ },
29964
+ {
29965
+ "tag": "SURNAME",
29966
+ "start": 5,
29967
+ "end": 12,
29968
+ "value": "Tsehaie"
29969
  },
29970
  {
29971
  "tag": "EMAIL",
 
30880
  {
30881
  "tag": "GIVENNAME",
30882
  "start": 49,
30883
+ "end": 57,
30884
+ "value": "Lawrence"
30885
+ },
30886
+ {
30887
+ "tag": "SURNAME",
30888
+ "start": 58,
30889
  "end": 63,
30890
+ "value": "Vicko"
30891
  },
30892
  {
30893
  "tag": "EMAIL",
 
31273
  {
31274
  "tag": "GIVENNAME",
31275
  "start": 27,
31276
+ "end": 39,
31277
+ "value": "Rajwinder Gi"
 
 
 
 
 
 
31278
  },
31279
  {
31280
  "tag": "IDCARDNUM",
 
31321
  ],
31322
  "predictions": [
31323
  {
31324
+ "tag": "SOCIALNUM",
31325
  "start": 47,
31326
  "end": 57,
31327
  "value": "0756957395"
 
31662
  {
31663
  "tag": "GIVENNAME",
31664
  "start": 34,
31665
+ "end": 45,
31666
+ "value": "Prerana Miñ"
31667
  },
31668
  {
31669
  "tag": "GIVENNAME",
 
31961
  "value": "Shkljzen"
31962
  },
31963
  {
31964
+ "tag": "IDCARDNUM",
31965
  "start": 58,
31966
+ "end": 68,
31967
+ "value": "4KIEV2OWI9"
31968
  }
31969
  ]
31970
  },
 
33125
  {
33126
  "tag": "TAXNUM",
33127
  "start": 129,
33128
+ "end": 131,
33129
+ "value": "56"
33130
  }
33131
  ]
33132
  },
 
33593
  {
33594
  "tag": "SURNAME",
33595
  "start": 43,
33596
+ "end": 45,
33597
+ "value": "Do"
33598
  },
33599
  {
33600
  "tag": "EMAIL",
 
33899
  ],
33900
  "predictions": [
33901
  {
33902
+ "tag": "SOCIALNUM",
33903
  "start": 20,
33904
+ "end": 22,
33905
+ "value": "09"
33906
  }
33907
  ]
33908
  },
 
34139
  "value": "Vannia Serafettin"
34140
  },
34141
  {
34142
+ "tag": "GIVENNAME",
34143
  "start": 71,
34144
  "end": 77,
34145
  "value": "Colusa"
 
34588
  {
34589
  "tag": "GIVENNAME",
34590
  "start": 90,
34591
+ "end": 99,
34592
+ "value": "Dastan Go"
34593
  },
34594
  {
34595
  "tag": "CITY",
 
34804
  {
34805
  "tag": "GIVENNAME",
34806
  "start": 28,
34807
+ "end": 31,
34808
+ "value": "War"
34809
  }
34810
  ]
34811
  },
 
35616
  {
35617
  "tag": "GIVENNAME",
35618
  "start": 16,
35619
+ "end": 22,
35620
+ "value": "Mayram"
35621
+ },
35622
+ {
35623
+ "tag": "SURNAME",
35624
+ "start": 23,
35625
  "end": 29,
35626
+ "value": "Janiel"
35627
  },
35628
  {
35629
  "tag": "DATE",
 
37285
  "value": "Muraleetharan Balraj"
37286
  },
37287
  {
37288
+ "tag": "GIVENNAME",
37289
  "start": 139,
37290
  "end": 145,
37291
  "value": "Jeevan"
 
38412
  {
38413
  "tag": "CITY",
38414
  "start": 93,
38415
+ "end": 103,
38416
+ "value": "Fairmeadow"
38417
  }
38418
  ]
38419
  },
ai4privacy/TokenBased-BERT/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32f180fda1cc3e0abeb3d5df703a0997be2c3b4b4212d652bc2f7527c678259
3
+ size 5265