Hugging Face's logo

PuxAI
/
GenPII-framework-Test

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
432ef18
·
verified ·
1 Parent(s): aba71c7

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. predictions_combined/en/span/eval_metrics.json +585 -0
  3. predictions_combined/en/span/predictions.json +3 -0
  4. predictions_combined/summary.json +325 -139
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  predictions_combined/en/bert_crf/predictions.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  predictions_combined/en/bert_crf/predictions.json filter=lfs diff=lfs merge=lfs -text
37
+ predictions_combined/en/span/predictions.json filter=lfs diff=lfs merge=lfs -text
predictions_combined/en/span/eval_metrics.json ADDED
@@ -0,0 +1,585 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.3268,
3
+ "recall": 0.4991,
4
+ "f1": 0.3903,
5
+ "total_samples": 1628,
6
+ "total_gt_entities": 20085,
7
+ "per_tag": {
8
+ "ACCOUNT_NAME": {
9
+ "precision": 0.0,
10
+ "recall": 0.0,
11
+ "f1": 0.0,
12
+ "support": 46
13
+ },
14
+ "ACCOUNT_NUMBER": {
15
+ "precision": 0.6036,
16
+ "recall": 0.8816,
17
+ "f1": 0.7166,
18
+ "support": 76
19
+ },
20
+ "AGE": {
21
+ "precision": 0.8328,
22
+ "recall": 0.9395,
23
+ "f1": 0.8829,
24
+ "support": 281
25
+ },
26
+ "AMOUNT": {
27
+ "precision": 0.0,
28
+ "recall": 0.0,
29
+ "f1": 0.0,
30
+ "support": 258
31
+ },
32
+ "API_KEY": {
33
+ "precision": 0.0,
34
+ "recall": 0.0,
35
+ "f1": 0.0,
36
+ "support": 0
37
+ },
38
+ "BANK_ROUTING_NUMBER": {
39
+ "precision": 0.0,
40
+ "recall": 0.0,
41
+ "f1": 0.0,
42
+ "support": 0
43
+ },
44
+ "BIC_SWIFT": {
45
+ "precision": 0.0,
46
+ "recall": 0.0,
47
+ "f1": 0.0,
48
+ "support": 35
49
+ },
50
+ "BIOMETRIC_DATA": {
51
+ "precision": 0.0,
52
+ "recall": 0.0,
53
+ "f1": 0.0,
54
+ "support": 4
55
+ },
56
+ "BIOMETRIC_IDENTIFIER": {
57
+ "precision": 0.0,
58
+ "recall": 0.0,
59
+ "f1": 0.0,
60
+ "support": 0
61
+ },
62
+ "BLOOD_TYPE": {
63
+ "precision": 0.0,
64
+ "recall": 0.0,
65
+ "f1": 0.0,
66
+ "support": 0
67
+ },
68
+ "BUILDING_NUMBER": {
69
+ "precision": 0.0,
70
+ "recall": 0.0,
71
+ "f1": 0.0,
72
+ "support": 479
73
+ },
74
+ "CERTIFICATE_LICENSE_NUMBER": {
75
+ "precision": 0.0,
76
+ "recall": 0.0,
77
+ "f1": 0.0,
78
+ "support": 0
79
+ },
80
+ "CITY": {
81
+ "precision": 0.4713,
82
+ "recall": 0.9435,
83
+ "f1": 0.6286,
84
+ "support": 584
85
+ },
86
+ "COMPANY_NAME": {
87
+ "precision": 0.5895,
88
+ "recall": 0.884,
89
+ "f1": 0.7073,
90
+ "support": 931
91
+ },
92
+ "COORDINATE": {
93
+ "precision": 0.0,
94
+ "recall": 0.0,
95
+ "f1": 0.0,
96
+ "support": 0
97
+ },
98
+ "COUNTRY": {
99
+ "precision": 0.0,
100
+ "recall": 0.0,
101
+ "f1": 0.0,
102
+ "support": 0
103
+ },
104
+ "COUNTY": {
105
+ "precision": 0.7208,
106
+ "recall": 0.9407,
107
+ "f1": 0.8162,
108
+ "support": 118
109
+ },
110
+ "CREDIT_CARD_CVV": {
111
+ "precision": 0.0,
112
+ "recall": 0.0,
113
+ "f1": 0.0,
114
+ "support": 16
115
+ },
116
+ "CREDIT_CARD_ISSUER": {
117
+ "precision": 0.0,
118
+ "recall": 0.0,
119
+ "f1": 0.0,
120
+ "support": 23
121
+ },
122
+ "CREDIT_CARD_NUMBER": {
123
+ "precision": 0.0,
124
+ "recall": 0.0,
125
+ "f1": 0.0,
126
+ "support": 19
127
+ },
128
+ "CREDIT_DEBIT_CARD": {
129
+ "precision": 0.0,
130
+ "recall": 0.0,
131
+ "f1": 0.0,
132
+ "support": 0
133
+ },
134
+ "CRIMINAL_RECORD": {
135
+ "precision": 0.0,
136
+ "recall": 0.0,
137
+ "f1": 0.0,
138
+ "support": 34
139
+ },
140
+ "CRYPTO_ADDRESS": {
141
+ "precision": 0.0,
142
+ "recall": 0.0,
143
+ "f1": 0.0,
144
+ "support": 17
145
+ },
146
+ "CUSTOMER_ID": {
147
+ "precision": 0.0,
148
+ "recall": 0.0,
149
+ "f1": 0.0,
150
+ "support": 0
151
+ },
152
+ "CVV": {
153
+ "precision": 0.0,
154
+ "recall": 0.0,
155
+ "f1": 0.0,
156
+ "support": 0
157
+ },
158
+ "DATE": {
159
+ "precision": 0.0,
160
+ "recall": 0.0,
161
+ "f1": 0.0,
162
+ "support": 0
163
+ },
164
+ "DATE_OF_BIRTH": {
165
+ "precision": 0.0,
166
+ "recall": 0.0,
167
+ "f1": 0.0,
168
+ "support": 0
169
+ },
170
+ "DATE_TIME": {
171
+ "precision": 0.0,
172
+ "recall": 0.0,
173
+ "f1": 0.0,
174
+ "support": 0
175
+ },
176
+ "DEATH_MISSING_DATE": {
177
+ "precision": 0.0,
178
+ "recall": 0.0,
179
+ "f1": 0.0,
180
+ "support": 189
181
+ },
182
+ "DEVICE_IDENTIFIER": {
183
+ "precision": 0.0,
184
+ "recall": 0.0,
185
+ "f1": 0.0,
186
+ "support": 0
187
+ },
188
+ "DOB": {
189
+ "precision": 0.0,
190
+ "recall": 0.0,
191
+ "f1": 0.0,
192
+ "support": 264
193
+ },
194
+ "DRIVER_LICENSE": {
195
+ "precision": 0.0,
196
+ "recall": 0.0,
197
+ "f1": 0.0,
198
+ "support": 51
199
+ },
200
+ "EDUCATION_LEVEL": {
201
+ "precision": 0.0,
202
+ "recall": 0.0,
203
+ "f1": 0.0,
204
+ "support": 0
205
+ },
206
+ "EMAIL": {
207
+ "precision": 0.8179,
208
+ "recall": 0.9805,
209
+ "f1": 0.8918,
210
+ "support": 513
211
+ },
212
+ "EMPLOYEE_ID": {
213
+ "precision": 0.0,
214
+ "recall": 0.0,
215
+ "f1": 0.0,
216
+ "support": 0
217
+ },
218
+ "EMPLOYMENT_STATUS": {
219
+ "precision": 0.0,
220
+ "recall": 0.0,
221
+ "f1": 0.0,
222
+ "support": 0
223
+ },
224
+ "ETHNICITY": {
225
+ "precision": 0.0,
226
+ "recall": 0.0,
227
+ "f1": 0.0,
228
+ "support": 87
229
+ },
230
+ "EYE_COLOR": {
231
+ "precision": 0.0,
232
+ "recall": 0.0,
233
+ "f1": 0.0,
234
+ "support": 15
235
+ },
236
+ "FAX_NUMBER": {
237
+ "precision": 0.0,
238
+ "recall": 0.0,
239
+ "f1": 0.0,
240
+ "support": 0
241
+ },
242
+ "FIRST_NAME": {
243
+ "precision": 0.4558,
244
+ "recall": 0.9177,
245
+ "f1": 0.6091,
246
+ "support": 2539
247
+ },
248
+ "GENDER": {
249
+ "precision": 0.3724,
250
+ "recall": 0.8923,
251
+ "f1": 0.5255,
252
+ "support": 260
253
+ },
254
+ "GPS_COORDINATE": {
255
+ "precision": 0.0,
256
+ "recall": 0.0,
257
+ "f1": 0.0,
258
+ "support": 346
259
+ },
260
+ "HEALTH_INSURANCE": {
261
+ "precision": 0.0,
262
+ "recall": 0.0,
263
+ "f1": 0.0,
264
+ "support": 20
265
+ },
266
+ "HEALTH_PLAN_BENEFICIARY_NUMBER": {
267
+ "precision": 0.0,
268
+ "recall": 0.0,
269
+ "f1": 0.0,
270
+ "support": 0
271
+ },
272
+ "HEALTH_STATUS": {
273
+ "precision": 0.0,
274
+ "recall": 0.0,
275
+ "f1": 0.0,
276
+ "support": 57
277
+ },
278
+ "HEIGHT": {
279
+ "precision": 0.0,
280
+ "recall": 0.0,
281
+ "f1": 0.0,
282
+ "support": 27
283
+ },
284
+ "HTTP_COOKIE": {
285
+ "precision": 0.0,
286
+ "recall": 0.0,
287
+ "f1": 0.0,
288
+ "support": 0
289
+ },
290
+ "IBAN": {
291
+ "precision": 0.0,
292
+ "recall": 0.0,
293
+ "f1": 0.0,
294
+ "support": 36
295
+ },
296
+ "IPV4": {
297
+ "precision": 0.9554,
298
+ "recall": 1.0,
299
+ "f1": 0.9772,
300
+ "support": 107
301
+ },
302
+ "IPV6": {
303
+ "precision": 0.8919,
304
+ "recall": 1.0,
305
+ "f1": 0.9429,
306
+ "support": 33
307
+ },
308
+ "JOB_AREA": {
309
+ "precision": 0.0,
310
+ "recall": 0.0,
311
+ "f1": 0.0,
312
+ "support": 381
313
+ },
314
+ "JOB_TYPE": {
315
+ "precision": 0.0,
316
+ "recall": 0.0,
317
+ "f1": 0.0,
318
+ "support": 1494
319
+ },
320
+ "LANGUAGE": {
321
+ "precision": 0.0,
322
+ "recall": 0.0,
323
+ "f1": 0.0,
324
+ "support": 0
325
+ },
326
+ "LAST_NAME": {
327
+ "precision": 0.5706,
328
+ "recall": 0.9046,
329
+ "f1": 0.6998,
330
+ "support": 2400
331
+ },
332
+ "LICENSE_PLATE": {
333
+ "precision": 0.0,
334
+ "recall": 0.0,
335
+ "f1": 0.0,
336
+ "support": 0
337
+ },
338
+ "MARITAL_STATUS": {
339
+ "precision": 0.0,
340
+ "recall": 0.0,
341
+ "f1": 0.0,
342
+ "support": 237
343
+ },
344
+ "MASKED_NUMBER": {
345
+ "precision": 0.0,
346
+ "recall": 0.0,
347
+ "f1": 0.0,
348
+ "support": 64
349
+ },
350
+ "MEDICAL_RECORD_NUMBER": {
351
+ "precision": 0.0,
352
+ "recall": 0.0,
353
+ "f1": 0.0,
354
+ "support": 0
355
+ },
356
+ "MEETING_DATE": {
357
+ "precision": 0.0,
358
+ "recall": 0.0,
359
+ "f1": 0.0,
360
+ "support": 1603
361
+ },
362
+ "MIDDLE_NAME": {
363
+ "precision": 0.0,
364
+ "recall": 0.0,
365
+ "f1": 0.0,
366
+ "support": 529
367
+ },
368
+ "NATIONALITY": {
369
+ "precision": 0.0,
370
+ "recall": 0.0,
371
+ "f1": 0.0,
372
+ "support": 237
373
+ },
374
+ "NATIONAL_ID": {
375
+ "precision": 0.0,
376
+ "recall": 0.0,
377
+ "f1": 0.0,
378
+ "support": 0
379
+ },
380
+ "OCCUPATION": {
381
+ "precision": 0.0,
382
+ "recall": 0.0,
383
+ "f1": 0.0,
384
+ "support": 0
385
+ },
386
+ "ORDINAL_DIRECTION": {
387
+ "precision": 0.0,
388
+ "recall": 0.0,
389
+ "f1": 0.0,
390
+ "support": 250
391
+ },
392
+ "PASSPORT_NUM": {
393
+ "precision": 0.0,
394
+ "recall": 0.0,
395
+ "f1": 0.0,
396
+ "support": 99
397
+ },
398
+ "PASSWORD": {
399
+ "precision": 0.4545,
400
+ "recall": 0.5556,
401
+ "f1": 0.5,
402
+ "support": 18
403
+ },
404
+ "PHONE_IMEI": {
405
+ "precision": 0.0,
406
+ "recall": 0.0,
407
+ "f1": 0.0,
408
+ "support": 32
409
+ },
410
+ "PHONE_NUMBER": {
411
+ "precision": 0.9224,
412
+ "recall": 0.9837,
413
+ "f1": 0.9521,
414
+ "support": 737
415
+ },
416
+ "PIN": {
417
+ "precision": 0.1557,
418
+ "recall": 0.7037,
419
+ "f1": 0.255,
420
+ "support": 27
421
+ },
422
+ "PLACE_OF_BIRTH": {
423
+ "precision": 0.0,
424
+ "recall": 0.0,
425
+ "f1": 0.0,
426
+ "support": 243
427
+ },
428
+ "POLITICAL_VIEW": {
429
+ "precision": 0.0,
430
+ "recall": 0.0,
431
+ "f1": 0.0,
432
+ "support": 0
433
+ },
434
+ "POSTCODE": {
435
+ "precision": 0.0,
436
+ "recall": 0.0,
437
+ "f1": 0.0,
438
+ "support": 0
439
+ },
440
+ "PREFIX": {
441
+ "precision": 0.0,
442
+ "recall": 0.0,
443
+ "f1": 0.0,
444
+ "support": 492
445
+ },
446
+ "RACE_ETHNICITY": {
447
+ "precision": 0.0,
448
+ "recall": 0.0,
449
+ "f1": 0.0,
450
+ "support": 0
451
+ },
452
+ "RELIGION": {
453
+ "precision": 0.0,
454
+ "recall": 0.0,
455
+ "f1": 0.0,
456
+ "support": 2
457
+ },
458
+ "RELIGIOUS_BELIEF": {
459
+ "precision": 0.0,
460
+ "recall": 0.0,
461
+ "f1": 0.0,
462
+ "support": 0
463
+ },
464
+ "SECONDARY_ADDRESS": {
465
+ "precision": 0.0,
466
+ "recall": 0.0,
467
+ "f1": 0.0,
468
+ "support": 222
469
+ },
470
+ "SEX": {
471
+ "precision": 0.0,
472
+ "recall": 0.0,
473
+ "f1": 0.0,
474
+ "support": 231
475
+ },
476
+ "SEXUALITY": {
477
+ "precision": 0.0,
478
+ "recall": 0.0,
479
+ "f1": 0.0,
480
+ "support": 0
481
+ },
482
+ "SSN": {
483
+ "precision": 0.0,
484
+ "recall": 0.0,
485
+ "f1": 0.0,
486
+ "support": 0
487
+ },
488
+ "SSN_CCCD": {
489
+ "precision": 0.0,
490
+ "recall": 0.0,
491
+ "f1": 0.0,
492
+ "support": 57
493
+ },
494
+ "STATE": {
495
+ "precision": 0.4906,
496
+ "recall": 0.8482,
497
+ "f1": 0.6216,
498
+ "support": 369
499
+ },
500
+ "STREET": {
501
+ "precision": 0.0,
502
+ "recall": 0.0,
503
+ "f1": 0.0,
504
+ "support": 415
505
+ },
506
+ "STREET_ADDRESS": {
507
+ "precision": 0.0,
508
+ "recall": 0.0,
509
+ "f1": 0.0,
510
+ "support": 0
511
+ },
512
+ "SWIFT_BIC": {
513
+ "precision": 0.0,
514
+ "recall": 0.0,
515
+ "f1": 0.0,
516
+ "support": 0
517
+ },
518
+ "TAX_ID": {
519
+ "precision": 0.764,
520
+ "recall": 0.7727,
521
+ "f1": 0.7684,
522
+ "support": 88
523
+ },
524
+ "TIME": {
525
+ "precision": 0.6884,
526
+ "recall": 0.958,
527
+ "f1": 0.8012,
528
+ "support": 1596
529
+ },
530
+ "TRADE_UNION_INFO": {
531
+ "precision": 0.0,
532
+ "recall": 0.0,
533
+ "f1": 0.0,
534
+ "support": 178
535
+ },
536
+ "UNIQUE_ID": {
537
+ "precision": 0.0,
538
+ "recall": 0.0,
539
+ "f1": 0.0,
540
+ "support": 0
541
+ },
542
+ "URL": {
543
+ "precision": 0.9286,
544
+ "recall": 0.9713,
545
+ "f1": 0.9494,
546
+ "support": 174
547
+ },
548
+ "USERNAME": {
549
+ "precision": 0.0,
550
+ "recall": 0.0,
551
+ "f1": 0.0,
552
+ "support": 123
553
+ },
554
+ "USER_NAME": {
555
+ "precision": 0.0,
556
+ "recall": 0.0,
557
+ "f1": 0.0,
558
+ "support": 0
559
+ },
560
+ "VEHICLE_IDENTIFIER": {
561
+ "precision": 0.0,
562
+ "recall": 0.0,
563
+ "f1": 0.0,
564
+ "support": 0
565
+ },
566
+ "VEHICLE_VIN": {
567
+ "precision": 0.0,
568
+ "recall": 0.0,
569
+ "f1": 0.0,
570
+ "support": 16
571
+ },
572
+ "VEHICLE_VRM": {
573
+ "precision": 0.0,
574
+ "recall": 0.0,
575
+ "f1": 0.0,
576
+ "support": 24
577
+ },
578
+ "ZIPCODE": {
579
+ "precision": 0.0,
580
+ "recall": 0.0,
581
+ "f1": 0.0,
582
+ "support": 282
583
+ }
584
+ }
585
+ }
predictions_combined/en/span/predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2a36291e7fb50c976032d4f4f6c5e449b0979f692d15af12054849fe60edb1
3
+ size 11671496
predictions_combined/summary.json CHANGED
@@ -1,22 +1,28 @@
1
  {
2
- "bert_crf": {
3
  "en": {
4
- "precision": 0.5655,
5
- "recall": 0.7164,
6
- "f1": 0.6123,
7
  "total_samples": 1628,
8
  "total_gt_entities": 20085,
9
  "per_tag": {
 
 
 
 
 
 
10
  "ACCOUNT_NUMBER": {
11
- "precision": 0.61,
12
- "recall": 0.5,
13
- "f1": 0.5495,
14
- "support": 122
15
  },
16
  "AGE": {
17
- "precision": 0.8951,
18
- "recall": 0.8505,
19
- "f1": 0.8723,
20
  "support": 281
21
  },
22
  "AMOUNT": {
@@ -37,12 +43,36 @@
37
  "f1": 0.0,
38
  "support": 0
39
  },
40
- "BIOMETRIC_IDENTIFIER": {
 
 
 
 
 
 
41
  "precision": 0.0,
42
  "recall": 0.0,
43
  "f1": 0.0,
44
  "support": 4
45
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  "CERTIFICATE_LICENSE_NUMBER": {
47
  "precision": 0.0,
48
  "recall": 0.0,
@@ -50,40 +80,58 @@
50
  "support": 0
51
  },
52
  "CITY": {
53
- "precision": 0.6991,
54
- "recall": 0.9214,
55
- "f1": 0.795,
56
- "support": 827
57
  },
58
  "COMPANY_NAME": {
59
- "precision": 0.666,
60
- "recall": 0.739,
61
- "f1": 0.7006,
62
  "support": 931
63
  },
64
  "COORDINATE": {
65
- "precision": 0.9024,
66
- "recall": 0.4277,
67
- "f1": 0.5804,
68
- "support": 346
69
  },
70
  "COUNTRY": {
71
- "precision": 0.0692,
72
- "recall": 0.0759,
73
- "f1": 0.0724,
74
- "support": 237
75
  },
76
  "COUNTY": {
77
- "precision": 0.7857,
78
- "recall": 0.9322,
79
- "f1": 0.8527,
80
  "support": 118
81
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
  "CREDIT_DEBIT_CARD": {
83
- "precision": 0.6316,
84
- "recall": 0.2857,
85
- "f1": 0.3934,
86
- "support": 42
87
  },
88
  "CRIMINAL_RECORD": {
89
  "precision": 0.0,
@@ -91,6 +139,12 @@
91
  "f1": 0.0,
92
  "support": 34
93
  },
 
 
 
 
 
 
94
  "CUSTOMER_ID": {
95
  "precision": 0.0,
96
  "recall": 0.0,
@@ -98,22 +152,22 @@
98
  "support": 0
99
  },
100
  "CVV": {
101
- "precision": 0.6667,
102
- "recall": 1.0,
103
- "f1": 0.8,
104
- "support": 16
105
  },
106
  "DATE": {
107
- "precision": 0.6217,
108
- "recall": 0.9392,
109
- "f1": 0.7482,
110
- "support": 1792
111
  },
112
  "DATE_OF_BIRTH": {
113
- "precision": 0.951,
114
- "recall": 0.5152,
115
- "f1": 0.6683,
116
- "support": 264
117
  },
118
  "DATE_TIME": {
119
  "precision": 0.0,
@@ -121,11 +175,29 @@
121
  "f1": 0.0,
122
  "support": 0
123
  },
 
 
 
 
 
 
124
  "DEVICE_IDENTIFIER": {
125
- "precision": 0.5938,
126
- "recall": 0.5938,
127
- "f1": 0.5938,
128
- "support": 32
 
 
 
 
 
 
 
 
 
 
 
 
129
  },
130
  "EDUCATION_LEVEL": {
131
  "precision": 0.0,
@@ -134,9 +206,9 @@
134
  "support": 0
135
  },
136
  "EMAIL": {
137
- "precision": 0.8253,
138
- "recall": 0.9669,
139
- "f1": 0.8905,
140
  "support": 513
141
  },
142
  "EMPLOYEE_ID": {
@@ -151,6 +223,12 @@
151
  "f1": 0.0,
152
  "support": 0
153
  },
 
 
 
 
 
 
154
  "EYE_COLOR": {
155
  "precision": 0.0,
156
  "recall": 0.0,
@@ -164,23 +242,35 @@
164
  "support": 0
165
  },
166
  "FIRST_NAME": {
167
- "precision": 0.4705,
168
- "recall": 0.9145,
169
- "f1": 0.6214,
170
  "support": 2539
171
  },
172
  "GENDER": {
173
- "precision": 0.8229,
174
- "recall": 0.7475,
175
- "f1": 0.7834,
176
- "support": 491
177
  },
178
- "HEALTH_PLAN_BENEFICIARY_NUMBER": {
179
- "precision": 0.0694,
180
- "recall": 0.25,
181
- "f1": 0.1087,
 
 
 
 
 
 
182
  "support": 20
183
  },
 
 
 
 
 
 
184
  "HEALTH_STATUS": {
185
  "precision": 0.0,
186
  "recall": 0.0,
@@ -206,17 +296,29 @@
206
  "support": 36
207
  },
208
  "IPV4": {
209
- "precision": 0.9722,
210
- "recall": 0.9813,
211
- "f1": 0.9767,
212
  "support": 107
213
  },
214
  "IPV6": {
215
- "precision": 0.9062,
216
- "recall": 0.8788,
217
- "f1": 0.8923,
218
  "support": 33
219
  },
 
 
 
 
 
 
 
 
 
 
 
 
220
  "LANGUAGE": {
221
  "precision": 0.0,
222
  "recall": 0.0,
@@ -224,9 +326,9 @@
224
  "support": 0
225
  },
226
  "LAST_NAME": {
227
- "precision": 0.5733,
228
- "recall": 0.89,
229
- "f1": 0.6974,
230
  "support": 2400
231
  },
232
  "LICENSE_PLATE": {
@@ -235,17 +337,17 @@
235
  "f1": 0.0,
236
  "support": 0
237
  },
238
- "MAC_ADDRESS": {
239
  "precision": 0.0,
240
  "recall": 0.0,
241
  "f1": 0.0,
242
- "support": 0
243
  },
244
- "MARITAL_STATUS": {
245
  "precision": 0.0,
246
  "recall": 0.0,
247
  "f1": 0.0,
248
- "support": 237
249
  },
250
  "MEDICAL_RECORD_NUMBER": {
251
  "precision": 0.0,
@@ -253,23 +355,35 @@
253
  "f1": 0.0,
254
  "support": 0
255
  },
 
 
 
 
 
 
256
  "MIDDLE_NAME": {
257
  "precision": 0.0,
258
  "recall": 0.0,
259
  "f1": 0.0,
260
  "support": 529
261
  },
 
 
 
 
 
 
262
  "NATIONAL_ID": {
263
- "precision": 0.3939,
264
- "recall": 0.0867,
265
- "f1": 0.1421,
266
- "support": 150
267
  },
268
  "OCCUPATION": {
269
- "precision": 0.4284,
270
- "recall": 0.7536,
271
- "f1": 0.5463,
272
- "support": 1875
273
  },
274
  "ORDINAL_DIRECTION": {
275
  "precision": 0.0,
@@ -277,24 +391,42 @@
277
  "f1": 0.0,
278
  "support": 250
279
  },
 
 
 
 
 
 
280
  "PASSWORD": {
281
- "precision": 0.3448,
282
  "recall": 0.5556,
283
- "f1": 0.4255,
284
  "support": 18
285
  },
 
 
 
 
 
 
286
  "PHONE_NUMBER": {
287
- "precision": 0.9181,
288
- "recall": 0.8969,
289
- "f1": 0.9073,
290
  "support": 737
291
  },
292
  "PIN": {
293
- "precision": 0.125,
294
- "recall": 0.7778,
295
- "f1": 0.2154,
296
  "support": 27
297
  },
 
 
 
 
 
 
298
  "POLITICAL_VIEW": {
299
  "precision": 0.0,
300
  "recall": 0.0,
@@ -302,10 +434,10 @@
302
  "support": 0
303
  },
304
  "POSTCODE": {
305
- "precision": 0.8037,
306
- "recall": 0.9291,
307
- "f1": 0.8618,
308
- "support": 282
309
  },
310
  "PREFIX": {
311
  "precision": 0.0,
@@ -314,17 +446,35 @@
314
  "support": 492
315
  },
316
  "RACE_ETHNICITY": {
317
- "precision": 0.2042,
318
- "recall": 0.5632,
319
- "f1": 0.2997,
320
- "support": 87
321
  },
322
- "RELIGIOUS_BELIEF": {
323
- "precision": 0.6667,
324
- "recall": 1.0,
325
- "f1": 0.8,
326
  "support": 2
327
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
328
  "SEXUALITY": {
329
  "precision": 0.0,
330
  "recall": 0.0,
@@ -332,39 +482,51 @@
332
  "support": 0
333
  },
334
  "SSN": {
335
- "precision": 0.8286,
336
- "recall": 0.5088,
337
- "f1": 0.6304,
 
 
 
 
 
 
338
  "support": 57
339
  },
340
  "STATE": {
341
- "precision": 0.4968,
342
  "recall": 0.8482,
343
- "f1": 0.6266,
344
  "support": 369
345
  },
 
 
 
 
 
 
346
  "STREET_ADDRESS": {
347
- "precision": 0.7784,
348
- "recall": 0.4722,
349
- "f1": 0.5878,
350
- "support": 1116
351
  },
352
  "SWIFT_BIC": {
353
- "precision": 0.6383,
354
- "recall": 0.8571,
355
- "f1": 0.7317,
356
- "support": 35
357
  },
358
  "TAX_ID": {
359
- "precision": 0.8025,
360
- "recall": 0.7386,
361
- "f1": 0.7692,
362
  "support": 88
363
  },
364
  "TIME": {
365
- "precision": 0.7632,
366
- "recall": 0.8584,
367
- "f1": 0.808,
368
  "support": 1596
369
  },
370
  "TRADE_UNION_INFO": {
@@ -374,28 +536,52 @@
374
  "support": 178
375
  },
376
  "UNIQUE_ID": {
377
- "precision": 0.0882,
378
- "recall": 0.037,
379
- "f1": 0.0522,
380
- "support": 81
381
  },
382
  "URL": {
383
- "precision": 0.9322,
384
- "recall": 0.9483,
385
- "f1": 0.9402,
386
  "support": 174
387
  },
388
- "USER_NAME": {
389
- "precision": 0.5697,
390
- "recall": 0.7642,
391
- "f1": 0.6528,
392
  "support": 123
393
  },
 
 
 
 
 
 
394
  "VEHICLE_IDENTIFIER": {
395
- "precision": 0.36,
396
- "recall": 0.225,
397
- "f1": 0.2769,
398
- "support": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
399
  }
400
  }
401
  }
 
1
  {
2
+ "span": {
3
  "en": {
4
+ "precision": 0.3268,
5
+ "recall": 0.4991,
6
+ "f1": 0.3903,
7
  "total_samples": 1628,
8
  "total_gt_entities": 20085,
9
  "per_tag": {
10
+ "ACCOUNT_NAME": {
11
+ "precision": 0.0,
12
+ "recall": 0.0,
13
+ "f1": 0.0,
14
+ "support": 46
15
+ },
16
  "ACCOUNT_NUMBER": {
17
+ "precision": 0.6036,
18
+ "recall": 0.8816,
19
+ "f1": 0.7166,
20
+ "support": 76
21
  },
22
  "AGE": {
23
+ "precision": 0.8328,
24
+ "recall": 0.9395,
25
+ "f1": 0.8829,
26
  "support": 281
27
  },
28
  "AMOUNT": {
 
43
  "f1": 0.0,
44
  "support": 0
45
  },
46
+ "BIC_SWIFT": {
47
+ "precision": 0.0,
48
+ "recall": 0.0,
49
+ "f1": 0.0,
50
+ "support": 35
51
+ },
52
+ "BIOMETRIC_DATA": {
53
  "precision": 0.0,
54
  "recall": 0.0,
55
  "f1": 0.0,
56
  "support": 4
57
  },
58
+ "BIOMETRIC_IDENTIFIER": {
59
+ "precision": 0.0,
60
+ "recall": 0.0,
61
+ "f1": 0.0,
62
+ "support": 0
63
+ },
64
+ "BLOOD_TYPE": {
65
+ "precision": 0.0,
66
+ "recall": 0.0,
67
+ "f1": 0.0,
68
+ "support": 0
69
+ },
70
+ "BUILDING_NUMBER": {
71
+ "precision": 0.0,
72
+ "recall": 0.0,
73
+ "f1": 0.0,
74
+ "support": 479
75
+ },
76
  "CERTIFICATE_LICENSE_NUMBER": {
77
  "precision": 0.0,
78
  "recall": 0.0,
 
80
  "support": 0
81
  },
82
  "CITY": {
83
+ "precision": 0.4713,
84
+ "recall": 0.9435,
85
+ "f1": 0.6286,
86
+ "support": 584
87
  },
88
  "COMPANY_NAME": {
89
+ "precision": 0.5895,
90
+ "recall": 0.884,
91
+ "f1": 0.7073,
92
  "support": 931
93
  },
94
  "COORDINATE": {
95
+ "precision": 0.0,
96
+ "recall": 0.0,
97
+ "f1": 0.0,
98
+ "support": 0
99
  },
100
  "COUNTRY": {
101
+ "precision": 0.0,
102
+ "recall": 0.0,
103
+ "f1": 0.0,
104
+ "support": 0
105
  },
106
  "COUNTY": {
107
+ "precision": 0.7208,
108
+ "recall": 0.9407,
109
+ "f1": 0.8162,
110
  "support": 118
111
  },
112
+ "CREDIT_CARD_CVV": {
113
+ "precision": 0.0,
114
+ "recall": 0.0,
115
+ "f1": 0.0,
116
+ "support": 16
117
+ },
118
+ "CREDIT_CARD_ISSUER": {
119
+ "precision": 0.0,
120
+ "recall": 0.0,
121
+ "f1": 0.0,
122
+ "support": 23
123
+ },
124
+ "CREDIT_CARD_NUMBER": {
125
+ "precision": 0.0,
126
+ "recall": 0.0,
127
+ "f1": 0.0,
128
+ "support": 19
129
+ },
130
  "CREDIT_DEBIT_CARD": {
131
+ "precision": 0.0,
132
+ "recall": 0.0,
133
+ "f1": 0.0,
134
+ "support": 0
135
  },
136
  "CRIMINAL_RECORD": {
137
  "precision": 0.0,
 
139
  "f1": 0.0,
140
  "support": 34
141
  },
142
+ "CRYPTO_ADDRESS": {
143
+ "precision": 0.0,
144
+ "recall": 0.0,
145
+ "f1": 0.0,
146
+ "support": 17
147
+ },
148
  "CUSTOMER_ID": {
149
  "precision": 0.0,
150
  "recall": 0.0,
 
152
  "support": 0
153
  },
154
  "CVV": {
155
+ "precision": 0.0,
156
+ "recall": 0.0,
157
+ "f1": 0.0,
158
+ "support": 0
159
  },
160
  "DATE": {
161
+ "precision": 0.0,
162
+ "recall": 0.0,
163
+ "f1": 0.0,
164
+ "support": 0
165
  },
166
  "DATE_OF_BIRTH": {
167
+ "precision": 0.0,
168
+ "recall": 0.0,
169
+ "f1": 0.0,
170
+ "support": 0
171
  },
172
  "DATE_TIME": {
173
  "precision": 0.0,
 
175
  "f1": 0.0,
176
  "support": 0
177
  },
178
+ "DEATH_MISSING_DATE": {
179
+ "precision": 0.0,
180
+ "recall": 0.0,
181
+ "f1": 0.0,
182
+ "support": 189
183
+ },
184
  "DEVICE_IDENTIFIER": {
185
+ "precision": 0.0,
186
+ "recall": 0.0,
187
+ "f1": 0.0,
188
+ "support": 0
189
+ },
190
+ "DOB": {
191
+ "precision": 0.0,
192
+ "recall": 0.0,
193
+ "f1": 0.0,
194
+ "support": 264
195
+ },
196
+ "DRIVER_LICENSE": {
197
+ "precision": 0.0,
198
+ "recall": 0.0,
199
+ "f1": 0.0,
200
+ "support": 51
201
  },
202
  "EDUCATION_LEVEL": {
203
  "precision": 0.0,
 
206
  "support": 0
207
  },
208
  "EMAIL": {
209
+ "precision": 0.8179,
210
+ "recall": 0.9805,
211
+ "f1": 0.8918,
212
  "support": 513
213
  },
214
  "EMPLOYEE_ID": {
 
223
  "f1": 0.0,
224
  "support": 0
225
  },
226
+ "ETHNICITY": {
227
+ "precision": 0.0,
228
+ "recall": 0.0,
229
+ "f1": 0.0,
230
+ "support": 87
231
+ },
232
  "EYE_COLOR": {
233
  "precision": 0.0,
234
  "recall": 0.0,
 
242
  "support": 0
243
  },
244
  "FIRST_NAME": {
245
+ "precision": 0.4558,
246
+ "recall": 0.9177,
247
+ "f1": 0.6091,
248
  "support": 2539
249
  },
250
  "GENDER": {
251
+ "precision": 0.3724,
252
+ "recall": 0.8923,
253
+ "f1": 0.5255,
254
+ "support": 260
255
  },
256
+ "GPS_COORDINATE": {
257
+ "precision": 0.0,
258
+ "recall": 0.0,
259
+ "f1": 0.0,
260
+ "support": 346
261
+ },
262
+ "HEALTH_INSURANCE": {
263
+ "precision": 0.0,
264
+ "recall": 0.0,
265
+ "f1": 0.0,
266
  "support": 20
267
  },
268
+ "HEALTH_PLAN_BENEFICIARY_NUMBER": {
269
+ "precision": 0.0,
270
+ "recall": 0.0,
271
+ "f1": 0.0,
272
+ "support": 0
273
+ },
274
  "HEALTH_STATUS": {
275
  "precision": 0.0,
276
  "recall": 0.0,
 
296
  "support": 36
297
  },
298
  "IPV4": {
299
+ "precision": 0.9554,
300
+ "recall": 1.0,
301
+ "f1": 0.9772,
302
  "support": 107
303
  },
304
  "IPV6": {
305
+ "precision": 0.8919,
306
+ "recall": 1.0,
307
+ "f1": 0.9429,
308
  "support": 33
309
  },
310
+ "JOB_AREA": {
311
+ "precision": 0.0,
312
+ "recall": 0.0,
313
+ "f1": 0.0,
314
+ "support": 381
315
+ },
316
+ "JOB_TYPE": {
317
+ "precision": 0.0,
318
+ "recall": 0.0,
319
+ "f1": 0.0,
320
+ "support": 1494
321
+ },
322
  "LANGUAGE": {
323
  "precision": 0.0,
324
  "recall": 0.0,
 
326
  "support": 0
327
  },
328
  "LAST_NAME": {
329
+ "precision": 0.5706,
330
+ "recall": 0.9046,
331
+ "f1": 0.6998,
332
  "support": 2400
333
  },
334
  "LICENSE_PLATE": {
 
337
  "f1": 0.0,
338
  "support": 0
339
  },
340
+ "MARITAL_STATUS": {
341
  "precision": 0.0,
342
  "recall": 0.0,
343
  "f1": 0.0,
344
+ "support": 237
345
  },
346
+ "MASKED_NUMBER": {
347
  "precision": 0.0,
348
  "recall": 0.0,
349
  "f1": 0.0,
350
+ "support": 64
351
  },
352
  "MEDICAL_RECORD_NUMBER": {
353
  "precision": 0.0,
 
355
  "f1": 0.0,
356
  "support": 0
357
  },
358
+ "MEETING_DATE": {
359
+ "precision": 0.0,
360
+ "recall": 0.0,
361
+ "f1": 0.0,
362
+ "support": 1603
363
+ },
364
  "MIDDLE_NAME": {
365
  "precision": 0.0,
366
  "recall": 0.0,
367
  "f1": 0.0,
368
  "support": 529
369
  },
370
+ "NATIONALITY": {
371
+ "precision": 0.0,
372
+ "recall": 0.0,
373
+ "f1": 0.0,
374
+ "support": 237
375
+ },
376
  "NATIONAL_ID": {
377
+ "precision": 0.0,
378
+ "recall": 0.0,
379
+ "f1": 0.0,
380
+ "support": 0
381
  },
382
  "OCCUPATION": {
383
+ "precision": 0.0,
384
+ "recall": 0.0,
385
+ "f1": 0.0,
386
+ "support": 0
387
  },
388
  "ORDINAL_DIRECTION": {
389
  "precision": 0.0,
 
391
  "f1": 0.0,
392
  "support": 250
393
  },
394
+ "PASSPORT_NUM": {
395
+ "precision": 0.0,
396
+ "recall": 0.0,
397
+ "f1": 0.0,
398
+ "support": 99
399
+ },
400
  "PASSWORD": {
401
+ "precision": 0.4545,
402
  "recall": 0.5556,
403
+ "f1": 0.5,
404
  "support": 18
405
  },
406
+ "PHONE_IMEI": {
407
+ "precision": 0.0,
408
+ "recall": 0.0,
409
+ "f1": 0.0,
410
+ "support": 32
411
+ },
412
  "PHONE_NUMBER": {
413
+ "precision": 0.9224,
414
+ "recall": 0.9837,
415
+ "f1": 0.9521,
416
  "support": 737
417
  },
418
  "PIN": {
419
+ "precision": 0.1557,
420
+ "recall": 0.7037,
421
+ "f1": 0.255,
422
  "support": 27
423
  },
424
+ "PLACE_OF_BIRTH": {
425
+ "precision": 0.0,
426
+ "recall": 0.0,
427
+ "f1": 0.0,
428
+ "support": 243
429
+ },
430
  "POLITICAL_VIEW": {
431
  "precision": 0.0,
432
  "recall": 0.0,
 
434
  "support": 0
435
  },
436
  "POSTCODE": {
437
+ "precision": 0.0,
438
+ "recall": 0.0,
439
+ "f1": 0.0,
440
+ "support": 0
441
  },
442
  "PREFIX": {
443
  "precision": 0.0,
 
446
  "support": 492
447
  },
448
  "RACE_ETHNICITY": {
449
+ "precision": 0.0,
450
+ "recall": 0.0,
451
+ "f1": 0.0,
452
+ "support": 0
453
  },
454
+ "RELIGION": {
455
+ "precision": 0.0,
456
+ "recall": 0.0,
457
+ "f1": 0.0,
458
  "support": 2
459
  },
460
+ "RELIGIOUS_BELIEF": {
461
+ "precision": 0.0,
462
+ "recall": 0.0,
463
+ "f1": 0.0,
464
+ "support": 0
465
+ },
466
+ "SECONDARY_ADDRESS": {
467
+ "precision": 0.0,
468
+ "recall": 0.0,
469
+ "f1": 0.0,
470
+ "support": 222
471
+ },
472
+ "SEX": {
473
+ "precision": 0.0,
474
+ "recall": 0.0,
475
+ "f1": 0.0,
476
+ "support": 231
477
+ },
478
  "SEXUALITY": {
479
  "precision": 0.0,
480
  "recall": 0.0,
 
482
  "support": 0
483
  },
484
  "SSN": {
485
+ "precision": 0.0,
486
+ "recall": 0.0,
487
+ "f1": 0.0,
488
+ "support": 0
489
+ },
490
+ "SSN_CCCD": {
491
+ "precision": 0.0,
492
+ "recall": 0.0,
493
+ "f1": 0.0,
494
  "support": 57
495
  },
496
  "STATE": {
497
+ "precision": 0.4906,
498
  "recall": 0.8482,
499
+ "f1": 0.6216,
500
  "support": 369
501
  },
502
+ "STREET": {
503
+ "precision": 0.0,
504
+ "recall": 0.0,
505
+ "f1": 0.0,
506
+ "support": 415
507
+ },
508
  "STREET_ADDRESS": {
509
+ "precision": 0.0,
510
+ "recall": 0.0,
511
+ "f1": 0.0,
512
+ "support": 0
513
  },
514
  "SWIFT_BIC": {
515
+ "precision": 0.0,
516
+ "recall": 0.0,
517
+ "f1": 0.0,
518
+ "support": 0
519
  },
520
  "TAX_ID": {
521
+ "precision": 0.764,
522
+ "recall": 0.7727,
523
+ "f1": 0.7684,
524
  "support": 88
525
  },
526
  "TIME": {
527
+ "precision": 0.6884,
528
+ "recall": 0.958,
529
+ "f1": 0.8012,
530
  "support": 1596
531
  },
532
  "TRADE_UNION_INFO": {
 
536
  "support": 178
537
  },
538
  "UNIQUE_ID": {
539
+ "precision": 0.0,
540
+ "recall": 0.0,
541
+ "f1": 0.0,
542
+ "support": 0
543
  },
544
  "URL": {
545
+ "precision": 0.9286,
546
+ "recall": 0.9713,
547
+ "f1": 0.9494,
548
  "support": 174
549
  },
550
+ "USERNAME": {
551
+ "precision": 0.0,
552
+ "recall": 0.0,
553
+ "f1": 0.0,
554
  "support": 123
555
  },
556
+ "USER_NAME": {
557
+ "precision": 0.0,
558
+ "recall": 0.0,
559
+ "f1": 0.0,
560
+ "support": 0
561
+ },
562
  "VEHICLE_IDENTIFIER": {
563
+ "precision": 0.0,
564
+ "recall": 0.0,
565
+ "f1": 0.0,
566
+ "support": 0
567
+ },
568
+ "VEHICLE_VIN": {
569
+ "precision": 0.0,
570
+ "recall": 0.0,
571
+ "f1": 0.0,
572
+ "support": 16
573
+ },
574
+ "VEHICLE_VRM": {
575
+ "precision": 0.0,
576
+ "recall": 0.0,
577
+ "f1": 0.0,
578
+ "support": 24
579
+ },
580
+ "ZIPCODE": {
581
+ "precision": 0.0,
582
+ "recall": 0.0,
583
+ "f1": 0.0,
584
+ "support": 282
585
  }
586
  }
587
  }