mvroz/dlp-poc-data / eval_smoke.json
mvroz's picture
download
raw
18.5 kB
{
"pii": [
{
"backend": "natasha",
"ner_P": 0.5166666666666667,
"ner_R": 0.28777777777777774,
"ner_F1_overlap": 0.35050505050505054,
"hybrid_P": 0.2111111111111111,
"hybrid_R": 0.13805555555555554,
"hybrid_F1_exact": 0.15531339031339034,
"per_type": {
"LOCATION": {
"tp": 5,
"fp": 9,
"fn": 30,
"f1": 0.20408163265306123,
"gold": 35
},
"PHONE": {
"tp": 4,
"fp": 2,
"fn": 21,
"f1": 0.25806451612903225,
"gold": 25
},
"URL": {
"tp": 0,
"fp": 0,
"fn": 5,
"f1": 0.0,
"gold": 5
},
"ORG": {
"tp": 0,
"fp": 6,
"fn": 0,
"f1": 0.0,
"gold": 0
},
"BIRTH_CERTIFICATE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"IP_ADDRESS": {
"tp": 0,
"fp": 0,
"fn": 3,
"f1": 0.0,
"gold": 3
},
"CREDIT_CARD": {
"tp": 0,
"fp": 0,
"fn": 7,
"f1": 0.0,
"gold": 7
},
"PERSON": {
"tp": 1,
"fp": 7,
"fn": 23,
"f1": 0.0625,
"gold": 24
},
"DRIVER_LICENSE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"PASSPORT": {
"tp": 0,
"fp": 1,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"INN": {
"tp": 0,
"fp": 0,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"OMS": {
"tp": 0,
"fp": 0,
"fn": 1,
"f1": 0.0,
"gold": 1
},
"SNILS": {
"tp": 0,
"fp": 0,
"fn": 13,
"f1": 0.0,
"gold": 13
}
},
"ms_per_text": 10757.184000006722
},
{
"backend": "spacy",
"ner_P": 0.5,
"ner_R": 0.2961111111111111,
"ner_F1_overlap": 0.35383838383838384,
"hybrid_P": 0.20555555555555557,
"hybrid_R": 0.15263888888888888,
"hybrid_F1_exact": 0.16861305361305362,
"per_type": {
"LOCATION": {
"tp": 6,
"fp": 7,
"fn": 30,
"f1": 0.2448979591836735,
"gold": 36
},
"PHONE": {
"tp": 4,
"fp": 2,
"fn": 21,
"f1": 0.25806451612903225,
"gold": 25
},
"URL": {
"tp": 0,
"fp": 0,
"fn": 5,
"f1": 0.0,
"gold": 5
},
"ORG": {
"tp": 0,
"fp": 8,
"fn": 0,
"f1": 0.0,
"gold": 0
},
"BIRTH_CERTIFICATE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"IP_ADDRESS": {
"tp": 0,
"fp": 0,
"fn": 3,
"f1": 0.0,
"gold": 3
},
"CREDIT_CARD": {
"tp": 0,
"fp": 0,
"fn": 7,
"f1": 0.0,
"gold": 7
},
"PERSON": {
"tp": 2,
"fp": 10,
"fn": 23,
"f1": 0.10810810810810811,
"gold": 25
},
"DRIVER_LICENSE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"PASSPORT": {
"tp": 0,
"fp": 1,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"INN": {
"tp": 0,
"fp": 0,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"OMS": {
"tp": 0,
"fp": 0,
"fn": 1,
"f1": 0.0,
"gold": 1
},
"SNILS": {
"tp": 0,
"fp": 0,
"fn": 13,
"f1": 0.0,
"gold": 13
}
},
"ms_per_text": 13332.997433341612
},
{
"backend": "gliner",
"ner_P": 0.51,
"ner_R": 0.32111111111111107,
"ner_F1_overlap": 0.3846031746031746,
"hybrid_P": 0.20396825396825397,
"hybrid_R": 0.15888888888888889,
"hybrid_F1_exact": 0.17328220893438287,
"per_type": {
"LOCATION": {
"tp": 8,
"fp": 14,
"fn": 30,
"f1": 0.26666666666666666,
"gold": 38
},
"PHONE": {
"tp": 4,
"fp": 2,
"fn": 21,
"f1": 0.25806451612903225,
"gold": 25
},
"URL": {
"tp": 0,
"fp": 0,
"fn": 5,
"f1": 0.0,
"gold": 5
},
"ORG": {
"tp": 0,
"fp": 5,
"fn": 0,
"f1": 0.0,
"gold": 0
},
"BIRTH_CERTIFICATE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"IP_ADDRESS": {
"tp": 0,
"fp": 0,
"fn": 3,
"f1": 0.0,
"gold": 3
},
"CREDIT_CARD": {
"tp": 0,
"fp": 0,
"fn": 7,
"f1": 0.0,
"gold": 7
},
"PERSON": {
"tp": 1,
"fp": 12,
"fn": 23,
"f1": 0.05405405405405406,
"gold": 24
},
"DRIVER_LICENSE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"PASSPORT": {
"tp": 0,
"fp": 1,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"INN": {
"tp": 0,
"fp": 0,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"OMS": {
"tp": 0,
"fp": 0,
"fn": 1,
"f1": 0.0,
"gold": 1
},
"SNILS": {
"tp": 0,
"fp": 0,
"fn": 13,
"f1": 0.0,
"gold": 13
}
},
"ms_per_text": 207551.31733349117
},
{
"backend": "rubert-tiny",
"ner_P": 0.4126923076923077,
"ner_R": 0.33111111111111113,
"ner_F1_overlap": 0.34394179894179894,
"hybrid_P": 0.14944444444444444,
"hybrid_R": 0.16861111111111113,
"hybrid_F1_exact": 0.14846153846153848,
"per_type": {
"LOCATION": {
"tp": 6,
"fp": 16,
"fn": 30,
"f1": 0.20689655172413793,
"gold": 36
},
"PHONE": {
"tp": 4,
"fp": 2,
"fn": 21,
"f1": 0.25806451612903225,
"gold": 25
},
"URL": {
"tp": 0,
"fp": 0,
"fn": 5,
"f1": 0.0,
"gold": 5
},
"PERSON": {
"tp": 3,
"fp": 17,
"fn": 23,
"f1": 0.13043478260869565,
"gold": 26
},
"ORG": {
"tp": 0,
"fp": 42,
"fn": 0,
"f1": 0.0,
"gold": 0
},
"BIRTH_CERTIFICATE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"IP_ADDRESS": {
"tp": 0,
"fp": 0,
"fn": 3,
"f1": 0.0,
"gold": 3
},
"CREDIT_CARD": {
"tp": 0,
"fp": 0,
"fn": 7,
"f1": 0.0,
"gold": 7
},
"DRIVER_LICENSE": {
"tp": 0,
"fp": 0,
"fn": 16,
"f1": 0.0,
"gold": 16
},
"PASSPORT": {
"tp": 0,
"fp": 1,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"INN": {
"tp": 0,
"fp": 0,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"OMS": {
"tp": 0,
"fp": 0,
"fn": 1,
"f1": 0.0,
"gold": 1
},
"SNILS": {
"tp": 0,
"fp": 0,
"fn": 13,
"f1": 0.0,
"gold": 13
}
},
"ms_per_text": 7855.007933176239
},
{
"backend": "piibert",
"ner_P": 0.43268518518518523,
"ner_R": 0.4888888888888889,
"ner_F1_overlap": 0.4296762496762497,
"hybrid_P": 0.22882275132275132,
"hybrid_R": 0.22777777777777777,
"hybrid_F1_exact": 0.21538677009265245,
"per_type": {
"LOCATION": {
"tp": 5,
"fp": 19,
"fn": 30,
"f1": 0.1694915254237288,
"gold": 35
},
"PHONE": {
"tp": 4,
"fp": 3,
"fn": 21,
"f1": 0.25,
"gold": 25
},
"URL": {
"tp": 0,
"fp": 2,
"fn": 5,
"f1": 0.0,
"gold": 5
},
"BIRTH_CERTIFICATE": {
"tp": 3,
"fp": 10,
"fn": 16,
"f1": 0.18749999999999997,
"gold": 19
},
"IP_ADDRESS": {
"tp": 1,
"fp": 6,
"fn": 3,
"f1": 0.18181818181818182,
"gold": 4
},
"CREDIT_CARD": {
"tp": 0,
"fp": 1,
"fn": 7,
"f1": 0.0,
"gold": 7
},
"PERSON": {
"tp": 7,
"fp": 38,
"fn": 23,
"f1": 0.18666666666666668,
"gold": 30
},
"DRIVER_LICENSE": {
"tp": 1,
"fp": 1,
"fn": 16,
"f1": 0.10526315789473684,
"gold": 17
},
"PASSPORT": {
"tp": 4,
"fp": 1,
"fn": 4,
"f1": 0.6153846153846154,
"gold": 8
},
"INN": {
"tp": 0,
"fp": 3,
"fn": 4,
"f1": 0.0,
"gold": 4
},
"OMS": {
"tp": 1,
"fp": 0,
"fn": 1,
"f1": 0.6666666666666666,
"gold": 2
},
"SNILS": {
"tp": 0,
"fp": 0,
"fn": 13,
"f1": 0.0,
"gold": 13
}
},
"ms_per_text": 10052.51956654926
},
{
"backend": "rules-only",
"hybrid_P": 0.13333333333333333,
"hybrid_R": 0.06111111111111111,
"hybrid_F1_exact": 0.07619047619047618
}
],
"synth": [
{
"backend": "natasha",
"ner_P": 0.22166666666666668,
"ner_R": 0.2775,
"ner_F1_overlap": 0.24033333333333332,
"hybrid_P": 0.5421666666666667,
"hybrid_R": 0.725,
"hybrid_F1_exact": 0.6046944444444444,
"per_type": {
"SNILS": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"PERSON": {
"tp": 45,
"fp": 250,
"fn": 89,
"f1": 0.20979020979020982,
"gold": 134
},
"PASSPORT": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"INN": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"CREDIT_CARD": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"PHONE": {
"tp": 88,
"fp": 5,
"fn": 88,
"f1": 0.654275092936803,
"gold": 176
},
"EMAIL": {
"tp": 44,
"fp": 0,
"fn": 44,
"f1": 0.6666666666666666,
"gold": 88
},
"LOCATION": {
"tp": 88,
"fp": 0,
"fn": 149,
"f1": 0.5415384615384616,
"gold": 237
}
},
"ms_per_text": 9419.264704974921
},
{
"backend": "spacy",
"ner_P": 0.2991666666666667,
"ner_R": 0.40875,
"ner_F1_overlap": 0.32916666666666666,
"hybrid_P": 0.545375,
"hybrid_R": 0.79125,
"hybrid_F1_exact": 0.6181111111111111,
"per_type": {
"SNILS": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"PERSON": {
"tp": 72,
"fp": 425,
"fn": 89,
"f1": 0.21884498480243164,
"gold": 161
},
"PASSPORT": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"INN": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"CREDIT_CARD": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"PHONE": {
"tp": 88,
"fp": 5,
"fn": 88,
"f1": 0.654275092936803,
"gold": 176
},
"EMAIL": {
"tp": 44,
"fp": 0,
"fn": 44,
"f1": 0.6666666666666666,
"gold": 88
},
"LOCATION": {
"tp": 102,
"fp": 28,
"fn": 149,
"f1": 0.5354330708661418,
"gold": 251
}
},
"ms_per_text": 11031.542515083856
},
{
"backend": "gliner",
"ner_P": 0.34875,
"ner_R": 0.44125,
"ner_F1_overlap": 0.3813333333333333,
"hybrid_P": 0.5895,
"hybrid_R": 0.8175,
"hybrid_F1_exact": 0.6709999999999999,
"per_type": {
"SNILS": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"PERSON": {
"tp": 85,
"fp": 260,
"fn": 89,
"f1": 0.3275529865125241,
"gold": 174
},
"PASSPORT": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"INN": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"CREDIT_CARD": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"PHONE": {
"tp": 88,
"fp": 5,
"fn": 88,
"f1": 0.654275092936803,
"gold": 176
},
"EMAIL": {
"tp": 44,
"fp": 0,
"fn": 44,
"f1": 0.6666666666666666,
"gold": 88
},
"LOCATION": {
"tp": 97,
"fp": 52,
"fn": 149,
"f1": 0.4911392405063291,
"gold": 246
},
"ORG": {
"tp": 0,
"fp": 1,
"fn": 0,
"f1": 0.0,
"gold": 0
}
},
"ms_per_text": 182073.10819500888
},
{
"backend": "rubert-tiny",
"ner_P": 0.13428688672438674,
"ner_R": 0.36875,
"ner_F1_overlap": 0.18176778776778776,
"hybrid_P": 0.293613455988456,
"hybrid_R": 0.704375,
"hybrid_F1_exact": 0.3995351662226662,
"per_type": {
"SNILS": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"PERSON": {
"tp": 39,
"fp": 532,
"fn": 89,
"f1": 0.11158798283261802,
"gold": 128
},
"ORG": {
"tp": 0,
"fp": 230,
"fn": 0,
"f1": 0.0,
"gold": 0
},
"PASSPORT": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"INN": {
"tp": 89,
"fp": 0,
"fn": 89,
"f1": 0.6666666666666666,
"gold": 178
},
"CREDIT_CARD": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"PHONE": {
"tp": 88,
"fp": 5,
"fn": 88,
"f1": 0.654275092936803,
"gold": 176
},
"EMAIL": {
"tp": 44,
"fp": 0,
"fn": 44,
"f1": 0.6666666666666666,
"gold": 88
},
"LOCATION": {
"tp": 69,
"fp": 389,
"fn": 149,
"f1": 0.20414201183431951,
"gold": 218
}
},
"ms_per_text": 4321.970642449742
},
{
"backend": "piibert",
"ner_P": 0.21507837301587301,
"ner_R": 0.4425,
"ner_F1_overlap": 0.26331944444444444,
"hybrid_P": 0.3608154761904762,
"hybrid_R": 0.6825,
"hybrid_F1_exact": 0.4408571428571429,
"per_type": {
"SNILS": {
"tp": 89,
"fp": 1,
"fn": 89,
"f1": 0.664179104477612,
"gold": 178
},
"PERSON": {
"tp": 4,
"fp": 919,
"fn": 89,
"f1": 0.007874015748031496,
"gold": 93
},
"PASSPORT": {
"tp": 45,
"fp": 29,
"fn": 45,
"f1": 0.5487804878048781,
"gold": 90
},
"INN": {
"tp": 89,
"fp": 14,
"fn": 89,
"f1": 0.6334519572953736,
"gold": 178
},
"CREDIT_CARD": {
"tp": 45,
"fp": 0,
"fn": 45,
"f1": 0.6666666666666666,
"gold": 90
},
"PHONE": {
"tp": 88,
"fp": 56,
"fn": 88,
"f1": 0.55,
"gold": 176
},
"EMAIL": {
"tp": 44,
"fp": 0,
"fn": 44,
"f1": 0.6666666666666666,
"gold": 88
},
"LOCATION": {
"tp": 95,
"fp": 100,
"fn": 149,
"f1": 0.4328018223234624,
"gold": 244
}
},
"ms_per_text": 9378.66909515833
},
{
"backend": "rules-only",
"hybrid_P": 0.67,
"hybrid_R": 0.58625,
"hybrid_F1_exact": 0.6167857142857143
}
]
}

Xet Storage Details

Size:
18.5 kB
·
Xet hash:
dc923636a76c978d592366b2014f183e02e45061656e5e61b3a7a62f4542b567

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.