PuxAI commited on
Commit
aba71c7
·
verified ·
1 Parent(s): 9a6c7a7

Upload folder using huggingface_hub

Browse files
predictions_combined/en/bert_crf/eval_metrics.json CHANGED
@@ -1,26 +1,20 @@
1
  {
2
- "precision": 0.0186,
3
- "recall": 0.0325,
4
- "f1": 0.0188,
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": 0.0,
16
- "recall": 0.0,
17
- "f1": 0.0,
18
- "support": 76
19
  },
20
  "AGE": {
21
- "precision": 0.0,
22
- "recall": 0.0,
23
- "f1": 0.0,
24
  "support": 281
25
  },
26
  "AMOUNT": {
@@ -41,35 +35,11 @@
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,
@@ -78,52 +48,40 @@
78
  "support": 0
79
  },
80
  "CITY": {
81
- "precision": 0.0,
82
- "recall": 0.0,
83
- "f1": 0.0,
84
- "support": 584
85
  },
86
  "COMPANY_NAME": {
87
- "precision": 0.0,
88
- "recall": 0.0,
89
- "f1": 0.0,
90
  "support": 931
91
  },
92
  "COORDINATE": {
93
- "precision": 0.0,
94
- "recall": 0.0,
95
- "f1": 0.0,
96
  "support": 346
97
  },
 
 
 
 
 
 
98
  "COUNTY": {
99
- "precision": 0.0,
100
- "recall": 0.0,
101
- "f1": 0.0,
102
  "support": 118
103
  },
104
- "CREDIT_CARD_CVV": {
105
- "precision": 0.0,
106
- "recall": 0.0,
107
- "f1": 0.0,
108
- "support": 16
109
- },
110
- "CREDIT_CARD_ISSUER": {
111
- "precision": 0.0,
112
- "recall": 0.0,
113
- "f1": 0.0,
114
- "support": 23
115
- },
116
- "CREDIT_CARD_NUMBER": {
117
- "precision": 0.0,
118
- "recall": 0.0,
119
- "f1": 0.0,
120
- "support": 19
121
- },
122
  "CREDIT_DEBIT_CARD": {
123
- "precision": 0.0,
124
- "recall": 0.0,
125
- "f1": 0.0,
126
- "support": 0
127
  },
128
  "CRIMINAL_RECORD": {
129
  "precision": 0.0,
@@ -131,29 +89,29 @@
131
  "f1": 0.0,
132
  "support": 34
133
  },
134
- "CRYPTO_ADDRESS": {
135
- "precision": 0.0,
136
- "recall": 0.0,
137
- "f1": 0.0,
138
- "support": 17
139
- },
140
  "CUSTOMER_ID": {
141
  "precision": 0.0,
142
  "recall": 0.0,
143
  "f1": 0.0,
144
  "support": 0
145
  },
 
 
 
 
 
 
146
  "DATE": {
147
- "precision": 0.0616,
148
- "recall": 0.0356,
149
- "f1": 0.0451,
150
- "support": 1603
151
  },
152
  "DATE_OF_BIRTH": {
153
- "precision": 0.0,
154
- "recall": 0.0,
155
- "f1": 0.0,
156
- "support": 0
157
  },
158
  "DATE_TIME": {
159
  "precision": 0.0,
@@ -161,30 +119,12 @@
161
  "f1": 0.0,
162
  "support": 0
163
  },
164
- "DEATH_MISSING_DATE": {
165
- "precision": 0.0,
166
- "recall": 0.0,
167
- "f1": 0.0,
168
- "support": 189
169
- },
170
  "DEVICE_IDENTIFIER": {
171
- "precision": 0.0,
172
- "recall": 0.0,
173
- "f1": 0.0,
174
  "support": 32
175
  },
176
- "DOB": {
177
- "precision": 0.0,
178
- "recall": 0.0,
179
- "f1": 0.0,
180
- "support": 264
181
- },
182
- "DRIVER_LICENSE": {
183
- "precision": 0.0,
184
- "recall": 0.0,
185
- "f1": 0.0,
186
- "support": 51
187
- },
188
  "EDUCATION_LEVEL": {
189
  "precision": 0.0,
190
  "recall": 0.0,
@@ -192,9 +132,9 @@
192
  "support": 0
193
  },
194
  "EMAIL": {
195
- "precision": 0.0,
196
- "recall": 0.0,
197
- "f1": 0.0,
198
  "support": 513
199
  },
200
  "EMPLOYEE_ID": {
@@ -203,11 +143,11 @@
203
  "f1": 0.0,
204
  "support": 0
205
  },
206
- "ETHNICITY": {
207
  "precision": 0.0,
208
  "recall": 0.0,
209
  "f1": 0.0,
210
- "support": 87
211
  },
212
  "EYE_COLOR": {
213
  "precision": 0.0,
@@ -222,21 +162,21 @@
222
  "support": 0
223
  },
224
  "FIRST_NAME": {
225
- "precision": 0.0513,
226
- "recall": 0.0248,
227
- "f1": 0.0335,
228
  "support": 2539
229
  },
230
  "GENDER": {
231
- "precision": 0.0,
232
- "recall": 0.0,
233
- "f1": 0.0,
234
  "support": 491
235
  },
236
  "HEALTH_PLAN_BENEFICIARY_NUMBER": {
237
- "precision": 0.0,
238
- "recall": 0.0,
239
- "f1": 0.0,
240
  "support": 20
241
  },
242
  "HEALTH_STATUS": {
@@ -264,15 +204,15 @@
264
  "support": 36
265
  },
266
  "IPV4": {
267
- "precision": 0.0,
268
- "recall": 0.0,
269
- "f1": 0.0,
270
  "support": 107
271
  },
272
  "IPV6": {
273
- "precision": 0.003,
274
- "recall": 0.0303,
275
- "f1": 0.0055,
276
  "support": 33
277
  },
278
  "LANGUAGE": {
@@ -282,9 +222,9 @@
282
  "support": 0
283
  },
284
  "LAST_NAME": {
285
- "precision": 0.0,
286
- "recall": 0.0,
287
- "f1": 0.0,
288
  "support": 2400
289
  },
290
  "LICENSE_PLATE": {
@@ -317,22 +257,16 @@
317
  "f1": 0.0,
318
  "support": 529
319
  },
320
- "NATIONALITY": {
321
- "precision": 0.0,
322
- "recall": 0.0,
323
- "f1": 0.0,
324
- "support": 237
325
- },
326
  "NATIONAL_ID": {
327
- "precision": 0.0,
328
- "recall": 0.0,
329
- "f1": 0.0,
330
- "support": 99
331
  },
332
  "OCCUPATION": {
333
- "precision": 0.0665,
334
- "recall": 0.2619,
335
- "f1": 0.106,
336
  "support": 1875
337
  },
338
  "ORDINAL_DIRECTION": {
@@ -342,33 +276,33 @@
342
  "support": 250
343
  },
344
  "PASSWORD": {
345
- "precision": 0.0,
346
- "recall": 0.0,
347
- "f1": 0.0,
348
  "support": 18
349
  },
350
  "PHONE_NUMBER": {
351
- "precision": 0.0,
352
- "recall": 0.0,
353
- "f1": 0.0,
354
  "support": 737
355
  },
356
  "PIN": {
357
- "precision": 0.0,
358
- "recall": 0.0,
359
- "f1": 0.0,
360
  "support": 27
361
  },
362
- "PLACE_OF_BIRTH": {
363
  "precision": 0.0,
364
  "recall": 0.0,
365
  "f1": 0.0,
366
- "support": 243
367
  },
368
  "POSTCODE": {
369
- "precision": 0.0,
370
- "recall": 0.0,
371
- "f1": 0.0,
372
  "support": 282
373
  },
374
  "PREFIX": {
@@ -378,23 +312,17 @@
378
  "support": 492
379
  },
380
  "RACE_ETHNICITY": {
381
- "precision": 0.0,
382
- "recall": 0.0,
383
- "f1": 0.0,
384
- "support": 0
385
  },
386
  "RELIGIOUS_BELIEF": {
387
- "precision": 0.0,
388
- "recall": 0.0,
389
- "f1": 0.0,
390
  "support": 2
391
  },
392
- "SECONDARY_ADDRESS": {
393
- "precision": 0.0,
394
- "recall": 0.0,
395
- "f1": 0.0,
396
- "support": 222
397
- },
398
  "SEXUALITY": {
399
  "precision": 0.0,
400
  "recall": 0.0,
@@ -402,39 +330,39 @@
402
  "support": 0
403
  },
404
  "SSN": {
405
- "precision": 0.0019,
406
- "recall": 0.0175,
407
- "f1": 0.0034,
408
  "support": 57
409
  },
410
  "STATE": {
411
- "precision": 0.0291,
412
- "recall": 0.0217,
413
- "f1": 0.0248,
414
  "support": 369
415
  },
416
  "STREET_ADDRESS": {
417
- "precision": 0.0117,
418
- "recall": 0.0193,
419
- "f1": 0.0146,
420
- "support": 415
421
  },
422
  "SWIFT_BIC": {
423
- "precision": 0.0,
424
- "recall": 0.0,
425
- "f1": 0.0,
426
- "support": 0
427
  },
428
  "TAX_ID": {
429
- "precision": 0.0052,
430
- "recall": 0.0114,
431
- "f1": 0.0071,
432
  "support": 88
433
  },
434
  "TIME": {
435
- "precision": 0.0,
436
- "recall": 0.0,
437
- "f1": 0.0,
438
  "support": 1596
439
  },
440
  "TRADE_UNION_INFO": {
@@ -444,27 +372,27 @@
444
  "support": 178
445
  },
446
  "UNIQUE_ID": {
447
- "precision": 0.0,
448
- "recall": 0.0,
449
- "f1": 0.0,
450
- "support": 64
451
  },
452
  "URL": {
453
- "precision": 0.0159,
454
- "recall": 0.0862,
455
- "f1": 0.0268,
456
  "support": 174
457
  },
458
  "USER_NAME": {
459
- "precision": 0.0036,
460
- "recall": 0.065,
461
- "f1": 0.0069,
462
  "support": 123
463
  },
464
  "VEHICLE_IDENTIFIER": {
465
- "precision": 0.0,
466
- "recall": 0.0,
467
- "f1": 0.0,
468
  "support": 40
469
  }
470
  }
 
1
  {
2
+ "precision": 0.5655,
3
+ "recall": 0.7164,
4
+ "f1": 0.6123,
5
  "total_samples": 1628,
6
  "total_gt_entities": 20085,
7
  "per_tag": {
 
 
 
 
 
 
8
  "ACCOUNT_NUMBER": {
9
+ "precision": 0.61,
10
+ "recall": 0.5,
11
+ "f1": 0.5495,
12
+ "support": 122
13
  },
14
  "AGE": {
15
+ "precision": 0.8951,
16
+ "recall": 0.8505,
17
+ "f1": 0.8723,
18
  "support": 281
19
  },
20
  "AMOUNT": {
 
35
  "f1": 0.0,
36
  "support": 0
37
  },
 
 
 
 
 
 
 
 
 
 
 
 
38
  "BIOMETRIC_IDENTIFIER": {
39
  "precision": 0.0,
40
  "recall": 0.0,
41
  "f1": 0.0,
42
+ "support": 4
 
 
 
 
 
 
 
 
 
 
 
 
43
  },
44
  "CERTIFICATE_LICENSE_NUMBER": {
45
  "precision": 0.0,
 
48
  "support": 0
49
  },
50
  "CITY": {
51
+ "precision": 0.6991,
52
+ "recall": 0.9214,
53
+ "f1": 0.795,
54
+ "support": 827
55
  },
56
  "COMPANY_NAME": {
57
+ "precision": 0.666,
58
+ "recall": 0.739,
59
+ "f1": 0.7006,
60
  "support": 931
61
  },
62
  "COORDINATE": {
63
+ "precision": 0.9024,
64
+ "recall": 0.4277,
65
+ "f1": 0.5804,
66
  "support": 346
67
  },
68
+ "COUNTRY": {
69
+ "precision": 0.0692,
70
+ "recall": 0.0759,
71
+ "f1": 0.0724,
72
+ "support": 237
73
+ },
74
  "COUNTY": {
75
+ "precision": 0.7857,
76
+ "recall": 0.9322,
77
+ "f1": 0.8527,
78
  "support": 118
79
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  "CREDIT_DEBIT_CARD": {
81
+ "precision": 0.6316,
82
+ "recall": 0.2857,
83
+ "f1": 0.3934,
84
+ "support": 42
85
  },
86
  "CRIMINAL_RECORD": {
87
  "precision": 0.0,
 
89
  "f1": 0.0,
90
  "support": 34
91
  },
 
 
 
 
 
 
92
  "CUSTOMER_ID": {
93
  "precision": 0.0,
94
  "recall": 0.0,
95
  "f1": 0.0,
96
  "support": 0
97
  },
98
+ "CVV": {
99
+ "precision": 0.6667,
100
+ "recall": 1.0,
101
+ "f1": 0.8,
102
+ "support": 16
103
+ },
104
  "DATE": {
105
+ "precision": 0.6217,
106
+ "recall": 0.9392,
107
+ "f1": 0.7482,
108
+ "support": 1792
109
  },
110
  "DATE_OF_BIRTH": {
111
+ "precision": 0.951,
112
+ "recall": 0.5152,
113
+ "f1": 0.6683,
114
+ "support": 264
115
  },
116
  "DATE_TIME": {
117
  "precision": 0.0,
 
119
  "f1": 0.0,
120
  "support": 0
121
  },
 
 
 
 
 
 
122
  "DEVICE_IDENTIFIER": {
123
+ "precision": 0.5938,
124
+ "recall": 0.5938,
125
+ "f1": 0.5938,
126
  "support": 32
127
  },
 
 
 
 
 
 
 
 
 
 
 
 
128
  "EDUCATION_LEVEL": {
129
  "precision": 0.0,
130
  "recall": 0.0,
 
132
  "support": 0
133
  },
134
  "EMAIL": {
135
+ "precision": 0.8253,
136
+ "recall": 0.9669,
137
+ "f1": 0.8905,
138
  "support": 513
139
  },
140
  "EMPLOYEE_ID": {
 
143
  "f1": 0.0,
144
  "support": 0
145
  },
146
+ "EMPLOYMENT_STATUS": {
147
  "precision": 0.0,
148
  "recall": 0.0,
149
  "f1": 0.0,
150
+ "support": 0
151
  },
152
  "EYE_COLOR": {
153
  "precision": 0.0,
 
162
  "support": 0
163
  },
164
  "FIRST_NAME": {
165
+ "precision": 0.4705,
166
+ "recall": 0.9145,
167
+ "f1": 0.6214,
168
  "support": 2539
169
  },
170
  "GENDER": {
171
+ "precision": 0.8229,
172
+ "recall": 0.7475,
173
+ "f1": 0.7834,
174
  "support": 491
175
  },
176
  "HEALTH_PLAN_BENEFICIARY_NUMBER": {
177
+ "precision": 0.0694,
178
+ "recall": 0.25,
179
+ "f1": 0.1087,
180
  "support": 20
181
  },
182
  "HEALTH_STATUS": {
 
204
  "support": 36
205
  },
206
  "IPV4": {
207
+ "precision": 0.9722,
208
+ "recall": 0.9813,
209
+ "f1": 0.9767,
210
  "support": 107
211
  },
212
  "IPV6": {
213
+ "precision": 0.9062,
214
+ "recall": 0.8788,
215
+ "f1": 0.8923,
216
  "support": 33
217
  },
218
  "LANGUAGE": {
 
222
  "support": 0
223
  },
224
  "LAST_NAME": {
225
+ "precision": 0.5733,
226
+ "recall": 0.89,
227
+ "f1": 0.6974,
228
  "support": 2400
229
  },
230
  "LICENSE_PLATE": {
 
257
  "f1": 0.0,
258
  "support": 529
259
  },
 
 
 
 
 
 
260
  "NATIONAL_ID": {
261
+ "precision": 0.3939,
262
+ "recall": 0.0867,
263
+ "f1": 0.1421,
264
+ "support": 150
265
  },
266
  "OCCUPATION": {
267
+ "precision": 0.4284,
268
+ "recall": 0.7536,
269
+ "f1": 0.5463,
270
  "support": 1875
271
  },
272
  "ORDINAL_DIRECTION": {
 
276
  "support": 250
277
  },
278
  "PASSWORD": {
279
+ "precision": 0.3448,
280
+ "recall": 0.5556,
281
+ "f1": 0.4255,
282
  "support": 18
283
  },
284
  "PHONE_NUMBER": {
285
+ "precision": 0.9181,
286
+ "recall": 0.8969,
287
+ "f1": 0.9073,
288
  "support": 737
289
  },
290
  "PIN": {
291
+ "precision": 0.125,
292
+ "recall": 0.7778,
293
+ "f1": 0.2154,
294
  "support": 27
295
  },
296
+ "POLITICAL_VIEW": {
297
  "precision": 0.0,
298
  "recall": 0.0,
299
  "f1": 0.0,
300
+ "support": 0
301
  },
302
  "POSTCODE": {
303
+ "precision": 0.8037,
304
+ "recall": 0.9291,
305
+ "f1": 0.8618,
306
  "support": 282
307
  },
308
  "PREFIX": {
 
312
  "support": 492
313
  },
314
  "RACE_ETHNICITY": {
315
+ "precision": 0.2042,
316
+ "recall": 0.5632,
317
+ "f1": 0.2997,
318
+ "support": 87
319
  },
320
  "RELIGIOUS_BELIEF": {
321
+ "precision": 0.6667,
322
+ "recall": 1.0,
323
+ "f1": 0.8,
324
  "support": 2
325
  },
 
 
 
 
 
 
326
  "SEXUALITY": {
327
  "precision": 0.0,
328
  "recall": 0.0,
 
330
  "support": 0
331
  },
332
  "SSN": {
333
+ "precision": 0.8286,
334
+ "recall": 0.5088,
335
+ "f1": 0.6304,
336
  "support": 57
337
  },
338
  "STATE": {
339
+ "precision": 0.4968,
340
+ "recall": 0.8482,
341
+ "f1": 0.6266,
342
  "support": 369
343
  },
344
  "STREET_ADDRESS": {
345
+ "precision": 0.7784,
346
+ "recall": 0.4722,
347
+ "f1": 0.5878,
348
+ "support": 1116
349
  },
350
  "SWIFT_BIC": {
351
+ "precision": 0.6383,
352
+ "recall": 0.8571,
353
+ "f1": 0.7317,
354
+ "support": 35
355
  },
356
  "TAX_ID": {
357
+ "precision": 0.8025,
358
+ "recall": 0.7386,
359
+ "f1": 0.7692,
360
  "support": 88
361
  },
362
  "TIME": {
363
+ "precision": 0.7632,
364
+ "recall": 0.8584,
365
+ "f1": 0.808,
366
  "support": 1596
367
  },
368
  "TRADE_UNION_INFO": {
 
372
  "support": 178
373
  },
374
  "UNIQUE_ID": {
375
+ "precision": 0.0882,
376
+ "recall": 0.037,
377
+ "f1": 0.0522,
378
+ "support": 81
379
  },
380
  "URL": {
381
+ "precision": 0.9322,
382
+ "recall": 0.9483,
383
+ "f1": 0.9402,
384
  "support": 174
385
  },
386
  "USER_NAME": {
387
+ "precision": 0.5697,
388
+ "recall": 0.7642,
389
+ "f1": 0.6528,
390
  "support": 123
391
  },
392
  "VEHICLE_IDENTIFIER": {
393
+ "precision": 0.36,
394
+ "recall": 0.225,
395
+ "f1": 0.2769,
396
  "support": 40
397
  }
398
  }
predictions_combined/en/bert_crf/predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a37f6c32ba24cc55d55ee23fa839ff2e8bd0937d4a7eee06ed0ad3eba0f3273
3
- size 51480135
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f7380fa32099fb59ffdaaf47e43a1af33a25cce44129bc75c0b445fa7a82df
3
+ size 9409441
predictions_combined/summary.json CHANGED
@@ -1,28 +1,22 @@
1
  {
2
  "bert_crf": {
3
  "en": {
4
- "precision": 0.0186,
5
- "recall": 0.0325,
6
- "f1": 0.0188,
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": 0.0,
18
- "recall": 0.0,
19
- "f1": 0.0,
20
- "support": 76
21
  },
22
  "AGE": {
23
- "precision": 0.0,
24
- "recall": 0.0,
25
- "f1": 0.0,
26
  "support": 281
27
  },
28
  "AMOUNT": {
@@ -43,35 +37,11 @@
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,
@@ -80,52 +50,40 @@
80
  "support": 0
81
  },
82
  "CITY": {
83
- "precision": 0.0,
84
- "recall": 0.0,
85
- "f1": 0.0,
86
- "support": 584
87
  },
88
  "COMPANY_NAME": {
89
- "precision": 0.0,
90
- "recall": 0.0,
91
- "f1": 0.0,
92
  "support": 931
93
  },
94
  "COORDINATE": {
95
- "precision": 0.0,
96
- "recall": 0.0,
97
- "f1": 0.0,
98
  "support": 346
99
  },
 
 
 
 
 
 
100
  "COUNTY": {
101
- "precision": 0.0,
102
- "recall": 0.0,
103
- "f1": 0.0,
104
  "support": 118
105
  },
106
- "CREDIT_CARD_CVV": {
107
- "precision": 0.0,
108
- "recall": 0.0,
109
- "f1": 0.0,
110
- "support": 16
111
- },
112
- "CREDIT_CARD_ISSUER": {
113
- "precision": 0.0,
114
- "recall": 0.0,
115
- "f1": 0.0,
116
- "support": 23
117
- },
118
- "CREDIT_CARD_NUMBER": {
119
- "precision": 0.0,
120
- "recall": 0.0,
121
- "f1": 0.0,
122
- "support": 19
123
- },
124
  "CREDIT_DEBIT_CARD": {
125
- "precision": 0.0,
126
- "recall": 0.0,
127
- "f1": 0.0,
128
- "support": 0
129
  },
130
  "CRIMINAL_RECORD": {
131
  "precision": 0.0,
@@ -133,29 +91,29 @@
133
  "f1": 0.0,
134
  "support": 34
135
  },
136
- "CRYPTO_ADDRESS": {
137
- "precision": 0.0,
138
- "recall": 0.0,
139
- "f1": 0.0,
140
- "support": 17
141
- },
142
  "CUSTOMER_ID": {
143
  "precision": 0.0,
144
  "recall": 0.0,
145
  "f1": 0.0,
146
  "support": 0
147
  },
 
 
 
 
 
 
148
  "DATE": {
149
- "precision": 0.0616,
150
- "recall": 0.0356,
151
- "f1": 0.0451,
152
- "support": 1603
153
  },
154
  "DATE_OF_BIRTH": {
155
- "precision": 0.0,
156
- "recall": 0.0,
157
- "f1": 0.0,
158
- "support": 0
159
  },
160
  "DATE_TIME": {
161
  "precision": 0.0,
@@ -163,30 +121,12 @@
163
  "f1": 0.0,
164
  "support": 0
165
  },
166
- "DEATH_MISSING_DATE": {
167
- "precision": 0.0,
168
- "recall": 0.0,
169
- "f1": 0.0,
170
- "support": 189
171
- },
172
  "DEVICE_IDENTIFIER": {
173
- "precision": 0.0,
174
- "recall": 0.0,
175
- "f1": 0.0,
176
  "support": 32
177
  },
178
- "DOB": {
179
- "precision": 0.0,
180
- "recall": 0.0,
181
- "f1": 0.0,
182
- "support": 264
183
- },
184
- "DRIVER_LICENSE": {
185
- "precision": 0.0,
186
- "recall": 0.0,
187
- "f1": 0.0,
188
- "support": 51
189
- },
190
  "EDUCATION_LEVEL": {
191
  "precision": 0.0,
192
  "recall": 0.0,
@@ -194,9 +134,9 @@
194
  "support": 0
195
  },
196
  "EMAIL": {
197
- "precision": 0.0,
198
- "recall": 0.0,
199
- "f1": 0.0,
200
  "support": 513
201
  },
202
  "EMPLOYEE_ID": {
@@ -205,11 +145,11 @@
205
  "f1": 0.0,
206
  "support": 0
207
  },
208
- "ETHNICITY": {
209
  "precision": 0.0,
210
  "recall": 0.0,
211
  "f1": 0.0,
212
- "support": 87
213
  },
214
  "EYE_COLOR": {
215
  "precision": 0.0,
@@ -224,21 +164,21 @@
224
  "support": 0
225
  },
226
  "FIRST_NAME": {
227
- "precision": 0.0513,
228
- "recall": 0.0248,
229
- "f1": 0.0335,
230
  "support": 2539
231
  },
232
  "GENDER": {
233
- "precision": 0.0,
234
- "recall": 0.0,
235
- "f1": 0.0,
236
  "support": 491
237
  },
238
  "HEALTH_PLAN_BENEFICIARY_NUMBER": {
239
- "precision": 0.0,
240
- "recall": 0.0,
241
- "f1": 0.0,
242
  "support": 20
243
  },
244
  "HEALTH_STATUS": {
@@ -266,15 +206,15 @@
266
  "support": 36
267
  },
268
  "IPV4": {
269
- "precision": 0.0,
270
- "recall": 0.0,
271
- "f1": 0.0,
272
  "support": 107
273
  },
274
  "IPV6": {
275
- "precision": 0.003,
276
- "recall": 0.0303,
277
- "f1": 0.0055,
278
  "support": 33
279
  },
280
  "LANGUAGE": {
@@ -284,9 +224,9 @@
284
  "support": 0
285
  },
286
  "LAST_NAME": {
287
- "precision": 0.0,
288
- "recall": 0.0,
289
- "f1": 0.0,
290
  "support": 2400
291
  },
292
  "LICENSE_PLATE": {
@@ -319,22 +259,16 @@
319
  "f1": 0.0,
320
  "support": 529
321
  },
322
- "NATIONALITY": {
323
- "precision": 0.0,
324
- "recall": 0.0,
325
- "f1": 0.0,
326
- "support": 237
327
- },
328
  "NATIONAL_ID": {
329
- "precision": 0.0,
330
- "recall": 0.0,
331
- "f1": 0.0,
332
- "support": 99
333
  },
334
  "OCCUPATION": {
335
- "precision": 0.0665,
336
- "recall": 0.2619,
337
- "f1": 0.106,
338
  "support": 1875
339
  },
340
  "ORDINAL_DIRECTION": {
@@ -344,33 +278,33 @@
344
  "support": 250
345
  },
346
  "PASSWORD": {
347
- "precision": 0.0,
348
- "recall": 0.0,
349
- "f1": 0.0,
350
  "support": 18
351
  },
352
  "PHONE_NUMBER": {
353
- "precision": 0.0,
354
- "recall": 0.0,
355
- "f1": 0.0,
356
  "support": 737
357
  },
358
  "PIN": {
359
- "precision": 0.0,
360
- "recall": 0.0,
361
- "f1": 0.0,
362
  "support": 27
363
  },
364
- "PLACE_OF_BIRTH": {
365
  "precision": 0.0,
366
  "recall": 0.0,
367
  "f1": 0.0,
368
- "support": 243
369
  },
370
  "POSTCODE": {
371
- "precision": 0.0,
372
- "recall": 0.0,
373
- "f1": 0.0,
374
  "support": 282
375
  },
376
  "PREFIX": {
@@ -380,23 +314,17 @@
380
  "support": 492
381
  },
382
  "RACE_ETHNICITY": {
383
- "precision": 0.0,
384
- "recall": 0.0,
385
- "f1": 0.0,
386
- "support": 0
387
  },
388
  "RELIGIOUS_BELIEF": {
389
- "precision": 0.0,
390
- "recall": 0.0,
391
- "f1": 0.0,
392
  "support": 2
393
  },
394
- "SECONDARY_ADDRESS": {
395
- "precision": 0.0,
396
- "recall": 0.0,
397
- "f1": 0.0,
398
- "support": 222
399
- },
400
  "SEXUALITY": {
401
  "precision": 0.0,
402
  "recall": 0.0,
@@ -404,39 +332,39 @@
404
  "support": 0
405
  },
406
  "SSN": {
407
- "precision": 0.0019,
408
- "recall": 0.0175,
409
- "f1": 0.0034,
410
  "support": 57
411
  },
412
  "STATE": {
413
- "precision": 0.0291,
414
- "recall": 0.0217,
415
- "f1": 0.0248,
416
  "support": 369
417
  },
418
  "STREET_ADDRESS": {
419
- "precision": 0.0117,
420
- "recall": 0.0193,
421
- "f1": 0.0146,
422
- "support": 415
423
  },
424
  "SWIFT_BIC": {
425
- "precision": 0.0,
426
- "recall": 0.0,
427
- "f1": 0.0,
428
- "support": 0
429
  },
430
  "TAX_ID": {
431
- "precision": 0.0052,
432
- "recall": 0.0114,
433
- "f1": 0.0071,
434
  "support": 88
435
  },
436
  "TIME": {
437
- "precision": 0.0,
438
- "recall": 0.0,
439
- "f1": 0.0,
440
  "support": 1596
441
  },
442
  "TRADE_UNION_INFO": {
@@ -446,27 +374,27 @@
446
  "support": 178
447
  },
448
  "UNIQUE_ID": {
449
- "precision": 0.0,
450
- "recall": 0.0,
451
- "f1": 0.0,
452
- "support": 64
453
  },
454
  "URL": {
455
- "precision": 0.0159,
456
- "recall": 0.0862,
457
- "f1": 0.0268,
458
  "support": 174
459
  },
460
  "USER_NAME": {
461
- "precision": 0.0036,
462
- "recall": 0.065,
463
- "f1": 0.0069,
464
  "support": 123
465
  },
466
  "VEHICLE_IDENTIFIER": {
467
- "precision": 0.0,
468
- "recall": 0.0,
469
- "f1": 0.0,
470
  "support": 40
471
  }
472
  }
 
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
  "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,
 
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
  "f1": 0.0,
92
  "support": 34
93
  },
 
 
 
 
 
 
94
  "CUSTOMER_ID": {
95
  "precision": 0.0,
96
  "recall": 0.0,
97
  "f1": 0.0,
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
  "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,
132
  "recall": 0.0,
 
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": {
 
145
  "f1": 0.0,
146
  "support": 0
147
  },
148
+ "EMPLOYMENT_STATUS": {
149
  "precision": 0.0,
150
  "recall": 0.0,
151
  "f1": 0.0,
152
+ "support": 0
153
  },
154
  "EYE_COLOR": {
155
  "precision": 0.0,
 
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": {
 
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": {
 
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": {
 
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": {
 
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,
301
  "f1": 0.0,
302
+ "support": 0
303
  },
304
  "POSTCODE": {
305
+ "precision": 0.8037,
306
+ "recall": 0.9291,
307
+ "f1": 0.8618,
308
  "support": 282
309
  },
310
  "PREFIX": {
 
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
  "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
  "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
  }