Hugging Face's logo

MinhTriet
/
ai4privacy-SpanBased-CustomDeBERTa

PyTorch
deberta-v2
Model card Files
xet
 Community
MinhTriet commited on
Commit
ade65d4
·
verified ·
1 Parent(s): 0d024f9

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. classification_report.json +122 -0
  2. config.json +85 -0
  3. predictions.json +2130 -0
  4. pytorch_model.bin +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +24 -0
classification_report.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "AGE": {
3
+ "precision": 0.0,
4
+ "recall": 0.0,
5
+ "f1-score": 0.0,
6
+ "support": 4
7
+ },
8
+ "BUILDINGNUM": {
9
+ "precision": 0.0,
10
+ "recall": 0.0,
11
+ "f1-score": 0.0,
12
+ "support": 8
13
+ },
14
+ "CITY": {
15
+ "precision": 0.0,
16
+ "recall": 0.0,
17
+ "f1-score": 0.0,
18
+ "support": 21
19
+ },
20
+ "CREDITCARDNUMBER": {
21
+ "precision": 0.0,
22
+ "recall": 0.0,
23
+ "f1-score": 0.0,
24
+ "support": 2
25
+ },
26
+ "DATE": {
27
+ "precision": 0.0,
28
+ "recall": 0.0,
29
+ "f1-score": 0.0,
30
+ "support": 15
31
+ },
32
+ "EMAIL": {
33
+ "precision": 0.0,
34
+ "recall": 0.0,
35
+ "f1-score": 0.0,
36
+ "support": 11
37
+ },
38
+ "GENDER": {
39
+ "precision": 0.0,
40
+ "recall": 0.0,
41
+ "f1-score": 0.0,
42
+ "support": 4
43
+ },
44
+ "GIVENNAME": {
45
+ "precision": 0.0,
46
+ "recall": 0.0,
47
+ "f1-score": 0.0,
48
+ "support": 87
49
+ },
50
+ "IDCARDNUM": {
51
+ "precision": 0.0,
52
+ "recall": 0.0,
53
+ "f1-score": 0.0,
54
+ "support": 11
55
+ },
56
+ "PASSPORTNUM": {
57
+ "precision": 0.0,
58
+ "recall": 0.0,
59
+ "f1-score": 0.0,
60
+ "support": 5
61
+ },
62
+ "SOCIALNUM": {
63
+ "precision": 0.0,
64
+ "recall": 0.0,
65
+ "f1-score": 0.0,
66
+ "support": 5
67
+ },
68
+ "STREET": {
69
+ "precision": 0.0,
70
+ "recall": 0.0,
71
+ "f1-score": 0.0,
72
+ "support": 11
73
+ },
74
+ "SURNAME": {
75
+ "precision": 0.0,
76
+ "recall": 0.0,
77
+ "f1-score": 0.0,
78
+ "support": 33
79
+ },
80
+ "TELEPHONENUM": {
81
+ "precision": 0.0,
82
+ "recall": 0.0,
83
+ "f1-score": 0.0,
84
+ "support": 14
85
+ },
86
+ "TIME": {
87
+ "precision": 0.0,
88
+ "recall": 0.0,
89
+ "f1-score": 0.0,
90
+ "support": 10
91
+ },
92
+ "TITLE": {
93
+ "precision": 0.0,
94
+ "recall": 0.0,
95
+ "f1-score": 0.0,
96
+ "support": 5
97
+ },
98
+ "ZIPCODE": {
99
+ "precision": 0.0,
100
+ "recall": 0.0,
101
+ "f1-score": 0.0,
102
+ "support": 9
103
+ },
104
+ "OVERALL_MICRO": {
105
+ "precision": 0.0,
106
+ "recall": 0.0,
107
+ "f1-score": 0.0,
108
+ "support": 255
109
+ },
110
+ "OVERALL_MACRO": {
111
+ "precision": 0.0,
112
+ "recall": 0.0,
113
+ "f1-score": 0.0,
114
+ "support": 255
115
+ },
116
+ "OVERALL_WEIGHTED": {
117
+ "precision": 0.0,
118
+ "recall": 0.0,
119
+ "f1-score": 0.0,
120
+ "support": 255
121
+ }
122
+ }
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaAdvancedSpanClassifier"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "AGE",
15
+ "2": "BUILDINGNUM",
16
+ "3": "CITY",
17
+ "4": "CREDITCARDNUMBER",
18
+ "5": "DATE",
19
+ "6": "DRIVERLICENSENUM",
20
+ "7": "EMAIL",
21
+ "8": "GENDER",
22
+ "9": "GIVENNAME",
23
+ "10": "IDCARDNUM",
24
+ "11": "PASSPORTNUM",
25
+ "12": "SEX",
26
+ "13": "SOCIALNUM",
27
+ "14": "STREET",
28
+ "15": "SURNAME",
29
+ "16": "TAXNUM",
30
+ "17": "TELEPHONENUM",
31
+ "18": "TIME",
32
+ "19": "TITLE",
33
+ "20": "ZIPCODE"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "AGE": 1,
39
+ "BUILDINGNUM": 2,
40
+ "CITY": 3,
41
+ "CREDITCARDNUMBER": 4,
42
+ "DATE": 5,
43
+ "DRIVERLICENSENUM": 6,
44
+ "EMAIL": 7,
45
+ "GENDER": 8,
46
+ "GIVENNAME": 9,
47
+ "IDCARDNUM": 10,
48
+ "O": 0,
49
+ "PASSPORTNUM": 11,
50
+ "SEX": 12,
51
+ "SOCIALNUM": 13,
52
+ "STREET": 14,
53
+ "SURNAME": 15,
54
+ "TAXNUM": 16,
55
+ "TELEPHONENUM": 17,
56
+ "TIME": 18,
57
+ "TITLE": 19,
58
+ "ZIPCODE": 20
59
+ },
60
+ "layer_norm_eps": 1e-07,
61
+ "legacy": true,
62
+ "max_position_embeddings": 384,
63
+ "max_relative_positions": -1,
64
+ "model_type": "deberta-v2",
65
+ "norm_rel_ebd": "layer_norm",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "pad_token_id": 0,
69
+ "pooler_dropout": 0.0,
70
+ "pooler_hidden_act": "gelu",
71
+ "pooler_hidden_size": 768,
72
+ "pos_att_type": [
73
+ "p2c",
74
+ "c2p"
75
+ ],
76
+ "position_biased_input": false,
77
+ "position_buckets": 256,
78
+ "relative_attention": true,
79
+ "share_att_key": true,
80
+ "tie_word_embeddings": true,
81
+ "transformers_version": "5.6.2",
82
+ "type_vocab_size": 0,
83
+ "use_cache": false,
84
+ "vocab_size": 128100
85
+ }
predictions.json ADDED
@@ -0,0 +1,2130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "source_text": "Dear Fetih, your application for the space simulation programme has been accepted. Please find the attached document for further details.",
4
+ "ground_truth": [
5
+ {
6
+ "tag": "GIVENNAME",
7
+ "value": "Fetih",
8
+ "start": 5,
9
+ "end": 10
10
+ }
11
+ ],
12
+ "predictions": []
13
+ },
14
+ {
15
+ "source_text": "Free Public Wi-Fi Hotspots in Wabush",
16
+ "ground_truth": [
17
+ {
18
+ "tag": "CITY",
19
+ "value": "Wabush",
20
+ "start": 30,
21
+ "end": 36
22
+ }
23
+ ],
24
+ "predictions": []
25
+ },
26
+ {
27
+ "source_text": "FI@gmail.com sent a request for a to-do list on woodworking tools.",
28
+ "ground_truth": [
29
+ {
30
+ "tag": "EMAIL",
31
+ "value": "FI@gmail.com",
32
+ "start": 0,
33
+ "end": 12
34
+ }
35
+ ],
36
+ "predictions": []
37
+ },
38
+ {
39
+ "source_text": "We appreciate your interest in the Pacific Islander Influences on modern architecture. Our team will be happy to provide you with more information on this topic, including examples of Palzom's work.",
40
+ "ground_truth": [
41
+ {
42
+ "tag": "GIVENNAME",
43
+ "value": "Palzom",
44
+ "start": 184,
45
+ "end": 190
46
+ }
47
+ ],
48
+ "predictions": []
49
+ },
50
+ {
51
+ "source_text": "Application for Thrift Store Seasonal Display: Arvi",
52
+ "ground_truth": [
53
+ {
54
+ "tag": "GIVENNAME",
55
+ "value": "Arvi",
56
+ "start": 47,
57
+ "end": 51
58
+ }
59
+ ],
60
+ "predictions": []
61
+ },
62
+ {
63
+ "source_text": "Dénise Dänger, Your (183)-6397735 has been registered as the contact number for the solar charging station setup.",
64
+ "ground_truth": [
65
+ {
66
+ "tag": "GIVENNAME",
67
+ "value": "Dénise",
68
+ "start": 0,
69
+ "end": 6
70
+ },
71
+ {
72
+ "tag": "SURNAME",
73
+ "value": "Dänger",
74
+ "start": 7,
75
+ "end": 13
76
+ },
77
+ {
78
+ "tag": "TELEPHONENUM",
79
+ "value": "(183)-6397735",
80
+ "start": 20,
81
+ "end": 33
82
+ }
83
+ ],
84
+ "predictions": []
85
+ },
86
+ {
87
+ "source_text": "Starr loves to spend time in their Duncan garden, surrounded by the G6G 0A1 beauty of nature and the QS8186071 wonder of growth.",
88
+ "ground_truth": [
89
+ {
90
+ "tag": "GIVENNAME",
91
+ "value": "Starr",
92
+ "start": 0,
93
+ "end": 5
94
+ },
95
+ {
96
+ "tag": "CITY",
97
+ "value": "Duncan",
98
+ "start": 35,
99
+ "end": 41
100
+ },
101
+ {
102
+ "tag": "ZIPCODE",
103
+ "value": "G6G 0A1",
104
+ "start": 68,
105
+ "end": 75
106
+ },
107
+ {
108
+ "tag": "PASSPORTNUM",
109
+ "value": "QS8186071",
110
+ "start": 101,
111
+ "end": 110
112
+ }
113
+ ],
114
+ "predictions": []
115
+ },
116
+ {
117
+ "source_text": "...",
118
+ "ground_truth": [],
119
+ "predictions": []
120
+ },
121
+ {
122
+ "source_text": "Hi Deni, we want to make sure you get the most out of our Planner Reflection Workshops. Can you please let us know your 22/02/2013?",
123
+ "ground_truth": [
124
+ {
125
+ "tag": "GIVENNAME",
126
+ "value": "Deni",
127
+ "start": 3,
128
+ "end": 7
129
+ },
130
+ {
131
+ "tag": "DATE",
132
+ "value": "22/02/2013",
133
+ "start": 120,
134
+ "end": 130
135
+ }
136
+ ],
137
+ "predictions": []
138
+ },
139
+ {
140
+ "source_text": "00.7011-7742 received an alert for a rural exploration diary entry at Greatham Road (114 - 118)",
141
+ "ground_truth": [
142
+ {
143
+ "tag": "TELEPHONENUM",
144
+ "value": "00.7011-7742",
145
+ "start": 0,
146
+ "end": 12
147
+ },
148
+ {
149
+ "tag": "STREET",
150
+ "value": "Greatham Road",
151
+ "start": 70,
152
+ "end": 83
153
+ },
154
+ {
155
+ "tag": "BUILDINGNUM",
156
+ "value": "(114 - 118)",
157
+ "start": 84,
158
+ "end": 95
159
+ }
160
+ ],
161
+ "predictions": []
162
+ },
163
+ {
164
+ "source_text": "Hi Keita Natacha, I need your KH86840VN to validate your identity.",
165
+ "ground_truth": [
166
+ {
167
+ "tag": "GIVENNAME",
168
+ "value": "Keita Natacha",
169
+ "start": 3,
170
+ "end": 16
171
+ },
172
+ {
173
+ "tag": "IDCARDNUM",
174
+ "value": "KH86840VN",
175
+ "start": 30,
176
+ "end": 39
177
+ }
178
+ ],
179
+ "predictions": []
180
+ },
181
+ {
182
+ "source_text": "Congratulations to Salvadora Kupf Otgonbaatar on winning the MVP award! Your gift card will be sent to Emsley Drive 74117",
183
+ "ground_truth": [
184
+ {
185
+ "tag": "GIVENNAME",
186
+ "value": "Salvadora",
187
+ "start": 19,
188
+ "end": 28
189
+ },
190
+ {
191
+ "tag": "SURNAME",
192
+ "value": "Kupf Otgonbaatar",
193
+ "start": 29,
194
+ "end": 45
195
+ },
196
+ {
197
+ "tag": "STREET",
198
+ "value": "Emsley Drive",
199
+ "start": 103,
200
+ "end": 115
201
+ },
202
+ {
203
+ "tag": "ZIPCODE",
204
+ "value": "74117",
205
+ "start": 116,
206
+ "end": 121
207
+ }
208
+ ],
209
+ "predictions": []
210
+ },
211
+ {
212
+ "source_text": "The bylaws require that all members provide their C5MSDGU8FC and T@aol.com.",
213
+ "ground_truth": [
214
+ {
215
+ "tag": "IDCARDNUM",
216
+ "value": "C5MSDGU8FC",
217
+ "start": 50,
218
+ "end": 60
219
+ },
220
+ {
221
+ "tag": "EMAIL",
222
+ "value": "T@aol.com",
223
+ "start": 65,
224
+ "end": 74
225
+ }
226
+ ],
227
+ "predictions": []
228
+ },
229
+ {
230
+ "source_text": "Form fill: Salvia's address is Veerasagara Main Road 2978, Ghatanji Rajendranagar",
231
+ "ground_truth": [
232
+ {
233
+ "tag": "GIVENNAME",
234
+ "value": "Salvia",
235
+ "start": 11,
236
+ "end": 17
237
+ },
238
+ {
239
+ "tag": "STREET",
240
+ "value": "Veerasagara Main Road",
241
+ "start": 31,
242
+ "end": 52
243
+ },
244
+ {
245
+ "tag": "BUILDINGNUM",
246
+ "value": "2978",
247
+ "start": 53,
248
+ "end": 57
249
+ },
250
+ {
251
+ "tag": "CITY",
252
+ "value": "Ghatanji Rajendranagar",
253
+ "start": 59,
254
+ "end": 81
255
+ }
256
+ ],
257
+ "predictions": []
258
+ },
259
+ {
260
+ "source_text": "Darrin Lingnardz Bakri's Climate Adaptation Measures: 0228141741",
261
+ "ground_truth": [
262
+ {
263
+ "tag": "GIVENNAME",
264
+ "value": "Darrin",
265
+ "start": 0,
266
+ "end": 6
267
+ },
268
+ {
269
+ "tag": "SURNAME",
270
+ "value": "Lingnardz Bakri",
271
+ "start": 7,
272
+ "end": 22
273
+ },
274
+ {
275
+ "tag": "SOCIALNUM",
276
+ "value": "0228141741",
277
+ "start": 54,
278
+ "end": 64
279
+ }
280
+ ],
281
+ "predictions": []
282
+ },
283
+ {
284
+ "source_text": "To finalize your citizenship application, please submit a copy of your OU6758730, CDBSROOFJA, and 8061505243.",
285
+ "ground_truth": [
286
+ {
287
+ "tag": "PASSPORTNUM",
288
+ "value": "OU6758730",
289
+ "start": 71,
290
+ "end": 80
291
+ },
292
+ {
293
+ "tag": "IDCARDNUM",
294
+ "value": "CDBSROOFJA",
295
+ "start": 82,
296
+ "end": 92
297
+ },
298
+ {
299
+ "tag": "SOCIALNUM",
300
+ "value": "8061505243",
301
+ "start": 98,
302
+ "end": 108
303
+ }
304
+ ],
305
+ "predictions": []
306
+ },
307
+ {
308
+ "source_text": "...",
309
+ "ground_truth": [],
310
+ "predictions": []
311
+ },
312
+ {
313
+ "source_text": "From: Aberash Bajrishe Cosmadopoulos\nTo: Sulayman Lorenzon\nSubject: Historical Import and Export via Rails\nHi Renu, I hope you're doing well. I've been going through some historical documents and I found some interesting information on the import and export via rails for Roosevelt. Would you like to take a look?",
314
+ "ground_truth": [
315
+ {
316
+ "tag": "GIVENNAME",
317
+ "value": "Aberash Bajrishe",
318
+ "start": 6,
319
+ "end": 22
320
+ },
321
+ {
322
+ "tag": "SURNAME",
323
+ "value": "Cosmadopoulos",
324
+ "start": 23,
325
+ "end": 36
326
+ },
327
+ {
328
+ "tag": "GIVENNAME",
329
+ "value": "Sulayman",
330
+ "start": 41,
331
+ "end": 49
332
+ },
333
+ {
334
+ "tag": "SURNAME",
335
+ "value": "Lorenzon",
336
+ "start": 50,
337
+ "end": 58
338
+ },
339
+ {
340
+ "tag": "GIVENNAME",
341
+ "value": "Renu",
342
+ "start": 110,
343
+ "end": 114
344
+ },
345
+ {
346
+ "tag": "CITY",
347
+ "value": "Roosevelt",
348
+ "start": 272,
349
+ "end": 281
350
+ }
351
+ ],
352
+ "predictions": []
353
+ },
354
+ {
355
+ "source_text": "Lorikë will ensure that the treehouse is designed with sustainable materials and meets the 32 building codes.",
356
+ "ground_truth": [
357
+ {
358
+ "tag": "GIVENNAME",
359
+ "value": "Lorikë",
360
+ "start": 0,
361
+ "end": 6
362
+ },
363
+ {
364
+ "tag": "AGE",
365
+ "value": "32",
366
+ "start": 91,
367
+ "end": 93
368
+ }
369
+ ],
370
+ "predictions": []
371
+ },
372
+ {
373
+ "source_text": "Please welcome Aran to the team.",
374
+ "ground_truth": [
375
+ {
376
+ "tag": "GIVENNAME",
377
+ "value": "Aran",
378
+ "start": 15,
379
+ "end": 19
380
+ }
381
+ ],
382
+ "predictions": []
383
+ },
384
+ {
385
+ "source_text": "Hi Ombeline Roxie, I'm so excited to start working on our treehouse project! I was thinking we could add a hidden room, just for us. What do you think, Nedzip?",
386
+ "ground_truth": [
387
+ {
388
+ "tag": "GIVENNAME",
389
+ "value": "Ombeline Roxie",
390
+ "start": 3,
391
+ "end": 17
392
+ },
393
+ {
394
+ "tag": "GIVENNAME",
395
+ "value": "Nedzip",
396
+ "start": 152,
397
+ "end": 158
398
+ }
399
+ ],
400
+ "predictions": []
401
+ },
402
+ {
403
+ "source_text": "I love the design on Jianying's birdhouse! Do you think I could get her +4.99-415 9321 number so I can ask her about it?",
404
+ "ground_truth": [
405
+ {
406
+ "tag": "GIVENNAME",
407
+ "value": "Jianying",
408
+ "start": 21,
409
+ "end": 29
410
+ },
411
+ {
412
+ "tag": "TELEPHONENUM",
413
+ "value": "+4.99-415 9321",
414
+ "start": 72,
415
+ "end": 86
416
+ }
417
+ ],
418
+ "predictions": []
419
+ },
420
+ {
421
+ "source_text": "0162 01.741-3374: Called Ioana-Andreea Bonnier and confirmed the catering order for February 27th, 1967's birthday party",
422
+ "ground_truth": [
423
+ {
424
+ "tag": "TELEPHONENUM",
425
+ "value": "0162 01.741-3374",
426
+ "start": 0,
427
+ "end": 16
428
+ },
429
+ {
430
+ "tag": "GIVENNAME",
431
+ "value": "Ioana-Andreea",
432
+ "start": 25,
433
+ "end": 38
434
+ },
435
+ {
436
+ "tag": "SURNAME",
437
+ "value": "Bonnier",
438
+ "start": 39,
439
+ "end": 46
440
+ },
441
+ {
442
+ "tag": "DATE",
443
+ "value": "February 27th, 1967",
444
+ "start": 84,
445
+ "end": 103
446
+ }
447
+ ],
448
+ "predictions": []
449
+ },
450
+ {
451
+ "source_text": "Subscription confirmation for Narjisse Migot on our newsletter: Medieval Garden Digest",
452
+ "ground_truth": [
453
+ {
454
+ "tag": "GIVENNAME",
455
+ "value": "Narjisse",
456
+ "start": 30,
457
+ "end": 38
458
+ },
459
+ {
460
+ "tag": "SURNAME",
461
+ "value": "Migot",
462
+ "start": 39,
463
+ "end": 44
464
+ }
465
+ ],
466
+ "predictions": []
467
+ },
468
+ {
469
+ "source_text": "Please provide your ZKSO2WCDUM and 4087818840 for verification purposes.",
470
+ "ground_truth": [
471
+ {
472
+ "tag": "IDCARDNUM",
473
+ "value": "ZKSO2WCDUM",
474
+ "start": 20,
475
+ "end": 30
476
+ },
477
+ {
478
+ "tag": "SOCIALNUM",
479
+ "value": "4087818840",
480
+ "start": 35,
481
+ "end": 45
482
+ }
483
+ ],
484
+ "predictions": []
485
+ },
486
+ {
487
+ "source_text": "During our family reunion, we'll be discussing our shared Ravikamatham Dahej roots and ancestry.",
488
+ "ground_truth": [
489
+ {
490
+ "tag": "CITY",
491
+ "value": "Ravikamatham Dahej",
492
+ "start": 58,
493
+ "end": 76
494
+ }
495
+ ],
496
+ "predictions": []
497
+ },
498
+ {
499
+ "source_text": "Hadie Mayada Newatu: Yeah, that's fine. The more the merrier!",
500
+ "ground_truth": [
501
+ {
502
+ "tag": "GIVENNAME",
503
+ "value": "Hadie Mayada",
504
+ "start": 0,
505
+ "end": 12
506
+ },
507
+ {
508
+ "tag": "SURNAME",
509
+ "value": "Newatu",
510
+ "start": 13,
511
+ "end": 19
512
+ }
513
+ ],
514
+ "predictions": []
515
+ },
516
+ {
517
+ "source_text": "Please submit your comments on the expansion plan to Z@yahoo.com by 25/09/1959.",
518
+ "ground_truth": [
519
+ {
520
+ "tag": "EMAIL",
521
+ "value": "Z@yahoo.com",
522
+ "start": 53,
523
+ "end": 64
524
+ },
525
+ {
526
+ "tag": "DATE",
527
+ "value": "25/09/1959",
528
+ "start": 68,
529
+ "end": 78
530
+ }
531
+ ],
532
+ "predictions": []
533
+ },
534
+ {
535
+ "source_text": "Jovanna Folasade Glomb is working on a life mapping log project to document the history of environmental regulations in Saint-Henri-de-Lévis, with a focus on 4th Line.",
536
+ "ground_truth": [
537
+ {
538
+ "tag": "GIVENNAME",
539
+ "value": "Jovanna Folasade",
540
+ "start": 0,
541
+ "end": 16
542
+ },
543
+ {
544
+ "tag": "SURNAME",
545
+ "value": "Glomb",
546
+ "start": 17,
547
+ "end": 22
548
+ },
549
+ {
550
+ "tag": "CITY",
551
+ "value": "Saint-Henri-de-Lévis",
552
+ "start": 120,
553
+ "end": 140
554
+ },
555
+ {
556
+ "tag": "STREET",
557
+ "value": "4th Line",
558
+ "start": 158,
559
+ "end": 166
560
+ }
561
+ ],
562
+ "predictions": []
563
+ },
564
+ {
565
+ "source_text": "Please confirm your availability for the meeting on 27/07/2010 at 00:17:49.",
566
+ "ground_truth": [
567
+ {
568
+ "tag": "DATE",
569
+ "value": "27/07/2010",
570
+ "start": 52,
571
+ "end": 62
572
+ },
573
+ {
574
+ "tag": "TIME",
575
+ "value": "00:17:49",
576
+ "start": 66,
577
+ "end": 74
578
+ }
579
+ ],
580
+ "predictions": []
581
+ },
582
+ {
583
+ "source_text": "Merry Christmas, Herminie Muhaber! 🎅",
584
+ "ground_truth": [
585
+ {
586
+ "tag": "GIVENNAME",
587
+ "value": "Herminie Muhaber",
588
+ "start": 17,
589
+ "end": 33
590
+ }
591
+ ],
592
+ "predictions": []
593
+ },
594
+ {
595
+ "source_text": "Looking for job training programs? We have openings in Datil.",
596
+ "ground_truth": [
597
+ {
598
+ "tag": "CITY",
599
+ "value": "Datil",
600
+ "start": 55,
601
+ "end": 60
602
+ }
603
+ ],
604
+ "predictions": []
605
+ },
606
+ {
607
+ "source_text": "Our office is located at Trinidad Drive 1386, Backus, 64130.",
608
+ "ground_truth": [
609
+ {
610
+ "tag": "STREET",
611
+ "value": "Trinidad Drive",
612
+ "start": 25,
613
+ "end": 39
614
+ },
615
+ {
616
+ "tag": "BUILDINGNUM",
617
+ "value": "1386",
618
+ "start": 40,
619
+ "end": 44
620
+ },
621
+ {
622
+ "tag": "CITY",
623
+ "value": "Backus",
624
+ "start": 46,
625
+ "end": 52
626
+ },
627
+ {
628
+ "tag": "ZIPCODE",
629
+ "value": "64130",
630
+ "start": 54,
631
+ "end": 59
632
+ }
633
+ ],
634
+ "predictions": []
635
+ },
636
+ {
637
+ "source_text": "Wenliang's poetry is not just written words, but artistry on parchment.",
638
+ "ground_truth": [
639
+ {
640
+ "tag": "GIVENNAME",
641
+ "value": "Wenliang",
642
+ "start": 0,
643
+ "end": 8
644
+ }
645
+ ],
646
+ "predictions": []
647
+ },
648
+ {
649
+ "source_text": "Eloïc Sofyan shared a file 'Ring Design Sketches2.zip': Here is the updated design concept for Silvère Abdeladim's ring.",
650
+ "ground_truth": [
651
+ {
652
+ "tag": "GIVENNAME",
653
+ "value": "Eloïc Sofyan",
654
+ "start": 0,
655
+ "end": 12
656
+ },
657
+ {
658
+ "tag": "GIVENNAME",
659
+ "value": "Silvère Abdeladim",
660
+ "start": 95,
661
+ "end": 112
662
+ }
663
+ ],
664
+ "predictions": []
665
+ },
666
+ {
667
+ "source_text": "Edmar has 349734576006955 and 47230 for delivery)",
668
+ "ground_truth": [
669
+ {
670
+ "tag": "GIVENNAME",
671
+ "value": "Edmar",
672
+ "start": 0,
673
+ "end": 5
674
+ },
675
+ {
676
+ "tag": "CREDITCARDNUMBER",
677
+ "value": "349734576006955",
678
+ "start": 10,
679
+ "end": 25
680
+ },
681
+ {
682
+ "tag": "ZIPCODE",
683
+ "value": "47230",
684
+ "start": 30,
685
+ "end": 35
686
+ }
687
+ ],
688
+ "predictions": []
689
+ },
690
+ {
691
+ "source_text": "As part of the cultural exchange program, Stanzl will be staying with a host family in Delta.",
692
+ "ground_truth": [
693
+ {
694
+ "tag": "SURNAME",
695
+ "value": "Stanzl",
696
+ "start": 42,
697
+ "end": 48
698
+ },
699
+ {
700
+ "tag": "CITY",
701
+ "value": "Delta",
702
+ "start": 87,
703
+ "end": 92
704
+ }
705
+ ],
706
+ "predictions": []
707
+ },
708
+ {
709
+ "source_text": "480-08-2001 reported a Female 3 bear in the Arvada Lamar Heights area.",
710
+ "ground_truth": [
711
+ {
712
+ "tag": "SOCIALNUM",
713
+ "value": "480-08-2001",
714
+ "start": 0,
715
+ "end": 11
716
+ },
717
+ {
718
+ "tag": "GENDER",
719
+ "value": "Female",
720
+ "start": 23,
721
+ "end": 29
722
+ },
723
+ {
724
+ "tag": "AGE",
725
+ "value": "3",
726
+ "start": 30,
727
+ "end": 31
728
+ },
729
+ {
730
+ "tag": "CITY",
731
+ "value": "Arvada Lamar Heights",
732
+ "start": 44,
733
+ "end": 64
734
+ }
735
+ ],
736
+ "predictions": []
737
+ },
738
+ {
739
+ "source_text": "11/11/1949 - Interoffice Correspondence: Alojzija Cernoch Fivet has been awarded the 'Most Improved Player' award in the gellyball tournament.",
740
+ "ground_truth": [
741
+ {
742
+ "tag": "DATE",
743
+ "value": "11/11/1949",
744
+ "start": 0,
745
+ "end": 10
746
+ },
747
+ {
748
+ "tag": "GIVENNAME",
749
+ "value": "Alojzija",
750
+ "start": 41,
751
+ "end": 49
752
+ },
753
+ {
754
+ "tag": "SURNAME",
755
+ "value": "Cernoch Fivet",
756
+ "start": 50,
757
+ "end": 63
758
+ }
759
+ ],
760
+ "predictions": []
761
+ },
762
+ {
763
+ "source_text": "Enilda Emelone's diary entry 29/01/1991: Successfully brewed 305814 IPA using Todapur Inner Road hops.",
764
+ "ground_truth": [
765
+ {
766
+ "tag": "GIVENNAME",
767
+ "value": "Enilda",
768
+ "start": 0,
769
+ "end": 6
770
+ },
771
+ {
772
+ "tag": "SURNAME",
773
+ "value": "Emelone",
774
+ "start": 7,
775
+ "end": 14
776
+ },
777
+ {
778
+ "tag": "DATE",
779
+ "value": "29/01/1991",
780
+ "start": 29,
781
+ "end": 39
782
+ },
783
+ {
784
+ "tag": "ZIPCODE",
785
+ "value": "305814",
786
+ "start": 61,
787
+ "end": 67
788
+ },
789
+ {
790
+ "tag": "STREET",
791
+ "value": "Todapur Inner Road",
792
+ "start": 78,
793
+ "end": 96
794
+ }
795
+ ],
796
+ "predictions": []
797
+ },
798
+ {
799
+ "source_text": "The league administrator, Alihan Eloan, has announced a new policy regarding player conduct.",
800
+ "ground_truth": [
801
+ {
802
+ "tag": "GIVENNAME",
803
+ "value": "Alihan Eloan",
804
+ "start": 26,
805
+ "end": 38
806
+ }
807
+ ],
808
+ "predictions": []
809
+ },
810
+ {
811
+ "source_text": "10:42 Amina: 'Hey Hazbije, I need help with setting up my treehouse art studio. Can you provide me with some ceramics crafting instructions?'",
812
+ "ground_truth": [
813
+ {
814
+ "tag": "TIME",
815
+ "value": "10:42",
816
+ "start": 0,
817
+ "end": 5
818
+ },
819
+ {
820
+ "tag": "GIVENNAME",
821
+ "value": "Amina",
822
+ "start": 6,
823
+ "end": 11
824
+ },
825
+ {
826
+ "tag": "GIVENNAME",
827
+ "value": "Hazbije",
828
+ "start": 18,
829
+ "end": 25
830
+ }
831
+ ],
832
+ "predictions": []
833
+ },
834
+ {
835
+ "source_text": "Nejc Gavin has written a poem for Nepa's birthday on 27/05/2010.",
836
+ "ground_truth": [
837
+ {
838
+ "tag": "GIVENNAME",
839
+ "value": "Nejc Gavin",
840
+ "start": 0,
841
+ "end": 10
842
+ },
843
+ {
844
+ "tag": "GIVENNAME",
845
+ "value": "Nepa",
846
+ "start": 34,
847
+ "end": 38
848
+ },
849
+ {
850
+ "tag": "DATE",
851
+ "value": "27/05/2010",
852
+ "start": 53,
853
+ "end": 63
854
+ }
855
+ ],
856
+ "predictions": []
857
+ },
858
+ {
859
+ "source_text": "16:42 Aomar: 'Hey Dilbrin, I loved your anti-gravity basket weaving design at the Dartmouth workshop.'",
860
+ "ground_truth": [
861
+ {
862
+ "tag": "TIME",
863
+ "value": "16:42",
864
+ "start": 0,
865
+ "end": 5
866
+ },
867
+ {
868
+ "tag": "GIVENNAME",
869
+ "value": "Aomar",
870
+ "start": 6,
871
+ "end": 11
872
+ },
873
+ {
874
+ "tag": "GIVENNAME",
875
+ "value": "Dilbrin",
876
+ "start": 18,
877
+ "end": 25
878
+ },
879
+ {
880
+ "tag": "CITY",
881
+ "value": "Dartmouth",
882
+ "start": 82,
883
+ "end": 91
884
+ }
885
+ ],
886
+ "predictions": []
887
+ },
888
+ {
889
+ "source_text": "Üsame Sivagnanasuntharam Moehr: Can we get an update on the seasonal updates memos?",
890
+ "ground_truth": [
891
+ {
892
+ "tag": "GIVENNAME",
893
+ "value": "Üsame",
894
+ "start": 0,
895
+ "end": 5
896
+ },
897
+ {
898
+ "tag": "SURNAME",
899
+ "value": "Sivagnanasuntharam Moehr",
900
+ "start": 6,
901
+ "end": 30
902
+ }
903
+ ],
904
+ "predictions": []
905
+ },
906
+ {
907
+ "source_text": "While browsing through Daymon's origami book, I stumbled upon a beautiful paper flower that I want to make for Dizara Valquiria's 18/04/1967 wedding anniversary.",
908
+ "ground_truth": [
909
+ {
910
+ "tag": "GIVENNAME",
911
+ "value": "Daymon",
912
+ "start": 23,
913
+ "end": 29
914
+ },
915
+ {
916
+ "tag": "GIVENNAME",
917
+ "value": "Dizara Valquiria",
918
+ "start": 111,
919
+ "end": 127
920
+ },
921
+ {
922
+ "tag": "DATE",
923
+ "value": "18/04/1967",
924
+ "start": 130,
925
+ "end": 140
926
+ }
927
+ ],
928
+ "predictions": []
929
+ },
930
+ {
931
+ "source_text": "quarter past 1 Neya: I've received the art collection records from Erduan Kenin D'albora. Let's schedule a time to review them.",
932
+ "ground_truth": [
933
+ {
934
+ "tag": "TIME",
935
+ "value": "quarter past 1",
936
+ "start": 0,
937
+ "end": 14
938
+ },
939
+ {
940
+ "tag": "GIVENNAME",
941
+ "value": "Neya",
942
+ "start": 15,
943
+ "end": 19
944
+ },
945
+ {
946
+ "tag": "GIVENNAME",
947
+ "value": "Erduan Kenin",
948
+ "start": 67,
949
+ "end": 79
950
+ },
951
+ {
952
+ "tag": "SURNAME",
953
+ "value": "D'albora",
954
+ "start": 80,
955
+ "end": 88
956
+ }
957
+ ],
958
+ "predictions": []
959
+ },
960
+ {
961
+ "source_text": "Dear Elijon Zabedin Qalandari Sikiric, please find attached your Space Simulation Participation Records. Your participant ID is VD76923JJ.",
962
+ "ground_truth": [
963
+ {
964
+ "tag": "GIVENNAME",
965
+ "value": "Elijon Zabedin",
966
+ "start": 5,
967
+ "end": 19
968
+ },
969
+ {
970
+ "tag": "SURNAME",
971
+ "value": "Qalandari Sikiric",
972
+ "start": 20,
973
+ "end": 37
974
+ },
975
+ {
976
+ "tag": "IDCARDNUM",
977
+ "value": "VD76923JJ",
978
+ "start": 128,
979
+ "end": 137
980
+ }
981
+ ],
982
+ "predictions": []
983
+ },
984
+ {
985
+ "source_text": "04:18 Shanaz: 'Looking forward to the Hepburn performance on 26/07/1944'",
986
+ "ground_truth": [
987
+ {
988
+ "tag": "TIME",
989
+ "value": "04:18",
990
+ "start": 0,
991
+ "end": 5
992
+ },
993
+ {
994
+ "tag": "GIVENNAME",
995
+ "value": "Shanaz",
996
+ "start": 6,
997
+ "end": 12
998
+ },
999
+ {
1000
+ "tag": "CITY",
1001
+ "value": "Hepburn",
1002
+ "start": 38,
1003
+ "end": 45
1004
+ },
1005
+ {
1006
+ "tag": "DATE",
1007
+ "value": "26/07/1944",
1008
+ "start": 61,
1009
+ "end": 71
1010
+ }
1011
+ ],
1012
+ "predictions": []
1013
+ },
1014
+ {
1015
+ "source_text": "Hi Ivanice, our team is working on your decade-specific clothing order, but we need to clarify some details. Can you please provide your 17 and F to ensure the best fit?",
1016
+ "ground_truth": [
1017
+ {
1018
+ "tag": "GIVENNAME",
1019
+ "value": "Ivanice",
1020
+ "start": 3,
1021
+ "end": 10
1022
+ },
1023
+ {
1024
+ "tag": "AGE",
1025
+ "value": "17",
1026
+ "start": 137,
1027
+ "end": 139
1028
+ },
1029
+ {
1030
+ "tag": "GENDER",
1031
+ "value": "F",
1032
+ "start": 144,
1033
+ "end": 145
1034
+ }
1035
+ ],
1036
+ "predictions": []
1037
+ },
1038
+ {
1039
+ "source_text": "Ainur's map art collection for Amber",
1040
+ "ground_truth": [
1041
+ {
1042
+ "tag": "GIVENNAME",
1043
+ "value": "Ainur",
1044
+ "start": 0,
1045
+ "end": 5
1046
+ },
1047
+ {
1048
+ "tag": "CITY",
1049
+ "value": "Amber",
1050
+ "start": 31,
1051
+ "end": 36
1052
+ }
1053
+ ],
1054
+ "predictions": []
1055
+ },
1056
+ {
1057
+ "source_text": "Jodie Hilf Passafiume has been assigned to guide you through the community outreach programme, please do not hesitate to contact them at 091-128.3183 if you have any questions or concerns.",
1058
+ "ground_truth": [
1059
+ {
1060
+ "tag": "GIVENNAME",
1061
+ "value": "Jodie",
1062
+ "start": 0,
1063
+ "end": 5
1064
+ },
1065
+ {
1066
+ "tag": "SURNAME",
1067
+ "value": "Hilf Passafiume",
1068
+ "start": 6,
1069
+ "end": 21
1070
+ },
1071
+ {
1072
+ "tag": "TELEPHONENUM",
1073
+ "value": "091-128.3183",
1074
+ "start": 137,
1075
+ "end": 149
1076
+ }
1077
+ ],
1078
+ "predictions": []
1079
+ },
1080
+ {
1081
+ "source_text": "I'm sending over our suggested integration designs to your M@aol.com with attachments.",
1082
+ "ground_truth": [
1083
+ {
1084
+ "tag": "EMAIL",
1085
+ "value": "M@aol.com",
1086
+ "start": 59,
1087
+ "end": 68
1088
+ }
1089
+ ],
1090
+ "predictions": []
1091
+ },
1092
+ {
1093
+ "source_text": "Hi Srbislava, hope you're doing well. We've been trying to reach you regarding your To-Do List submission. Could you please get back to us at +4454712-0464 or evguetinella@gmail.com?",
1094
+ "ground_truth": [
1095
+ {
1096
+ "tag": "GIVENNAME",
1097
+ "value": "Srbislava",
1098
+ "start": 3,
1099
+ "end": 12
1100
+ },
1101
+ {
1102
+ "tag": "TELEPHONENUM",
1103
+ "value": "+4454712-0464",
1104
+ "start": 142,
1105
+ "end": 155
1106
+ },
1107
+ {
1108
+ "tag": "EMAIL",
1109
+ "value": "evguetinella@gmail.com",
1110
+ "start": 159,
1111
+ "end": 181
1112
+ }
1113
+ ],
1114
+ "predictions": []
1115
+ },
1116
+ {
1117
+ "source_text": "Skybound with Orestina Zizë at the Shahapur Gatarad Village kite festival",
1118
+ "ground_truth": [
1119
+ {
1120
+ "tag": "GIVENNAME",
1121
+ "value": "Orestina Zizë",
1122
+ "start": 14,
1123
+ "end": 27
1124
+ },
1125
+ {
1126
+ "tag": "CITY",
1127
+ "value": "Shahapur Gatarad Village",
1128
+ "start": 35,
1129
+ "end": 59
1130
+ }
1131
+ ],
1132
+ "predictions": []
1133
+ },
1134
+ {
1135
+ "source_text": "+3.036-244 1257 sent a message: 'Hey, can we talk about tolerance in conversations? I've been feeling really frustrated with some friends lately...'",
1136
+ "ground_truth": [
1137
+ {
1138
+ "tag": "TELEPHONENUM",
1139
+ "value": "+3.036-244 1257",
1140
+ "start": 0,
1141
+ "end": 15
1142
+ }
1143
+ ],
1144
+ "predictions": []
1145
+ },
1146
+ {
1147
+ "source_text": "Tasin Luano Pfahrer won the family game night trophy!",
1148
+ "ground_truth": [
1149
+ {
1150
+ "tag": "GIVENNAME",
1151
+ "value": "Tasin Luano",
1152
+ "start": 0,
1153
+ "end": 11
1154
+ },
1155
+ {
1156
+ "tag": "SURNAME",
1157
+ "value": "Pfahrer",
1158
+ "start": 12,
1159
+ "end": 19
1160
+ }
1161
+ ],
1162
+ "predictions": []
1163
+ },
1164
+ {
1165
+ "source_text": "Happy birthday to Vrona! Hope you have a fantastic day.",
1166
+ "ground_truth": [
1167
+ {
1168
+ "tag": "GIVENNAME",
1169
+ "value": "Vrona",
1170
+ "start": 18,
1171
+ "end": 23
1172
+ }
1173
+ ],
1174
+ "predictions": []
1175
+ },
1176
+ {
1177
+ "source_text": "Contact Cataleya at +288 08.694.6514 to participate in Ofc",
1178
+ "ground_truth": [
1179
+ {
1180
+ "tag": "GIVENNAME",
1181
+ "value": "Cataleya",
1182
+ "start": 8,
1183
+ "end": 16
1184
+ },
1185
+ {
1186
+ "tag": "TELEPHONENUM",
1187
+ "value": "+288 08.694.6514",
1188
+ "start": 20,
1189
+ "end": 36
1190
+ },
1191
+ {
1192
+ "tag": "TITLE",
1193
+ "value": "Ofc",
1194
+ "start": 55,
1195
+ "end": 58
1196
+ }
1197
+ ],
1198
+ "predictions": []
1199
+ },
1200
+ {
1201
+ "source_text": "Monitoring Log #TPQ321B72K: At 7:39 on October 22nd, 1962, Woody Skarzynski measured the water quality parameters in the nearby wetlands.",
1202
+ "ground_truth": [
1203
+ {
1204
+ "tag": "IDCARDNUM",
1205
+ "value": "TPQ321B72K",
1206
+ "start": 16,
1207
+ "end": 26
1208
+ },
1209
+ {
1210
+ "tag": "TIME",
1211
+ "value": "7:39",
1212
+ "start": 31,
1213
+ "end": 35
1214
+ },
1215
+ {
1216
+ "tag": "DATE",
1217
+ "value": "October 22nd, 1962",
1218
+ "start": 39,
1219
+ "end": 57
1220
+ },
1221
+ {
1222
+ "tag": "GIVENNAME",
1223
+ "value": "Woody",
1224
+ "start": 59,
1225
+ "end": 64
1226
+ },
1227
+ {
1228
+ "tag": "SURNAME",
1229
+ "value": "Skarzynski",
1230
+ "start": 65,
1231
+ "end": 75
1232
+ }
1233
+ ],
1234
+ "predictions": []
1235
+ },
1236
+ {
1237
+ "source_text": "Text Message: Hi Noely Henrieta, please submit your grievance letter regarding the peer mentorship program by 28th March 2023 to mescholt@aol.com",
1238
+ "ground_truth": [
1239
+ {
1240
+ "tag": "GIVENNAME",
1241
+ "value": "Noely Henrieta",
1242
+ "start": 17,
1243
+ "end": 31
1244
+ },
1245
+ {
1246
+ "tag": "DATE",
1247
+ "value": "28th March 2023",
1248
+ "start": 110,
1249
+ "end": 125
1250
+ },
1251
+ {
1252
+ "tag": "EMAIL",
1253
+ "value": "mescholt@aol.com",
1254
+ "start": 129,
1255
+ "end": 145
1256
+ }
1257
+ ],
1258
+ "predictions": []
1259
+ },
1260
+ {
1261
+ "source_text": "Please review the attached education plan and confirm your Dodo and SA50045VL for verification.",
1262
+ "ground_truth": [
1263
+ {
1264
+ "tag": "GIVENNAME",
1265
+ "value": "Dodo",
1266
+ "start": 59,
1267
+ "end": 63
1268
+ },
1269
+ {
1270
+ "tag": "IDCARDNUM",
1271
+ "value": "SA50045VL",
1272
+ "start": 68,
1273
+ "end": 77
1274
+ }
1275
+ ],
1276
+ "predictions": []
1277
+ },
1278
+ {
1279
+ "source_text": "We've posted the formal garden design plans for the monastery in our closed Y1952@hotmail.com group, requiring access via member's UB50272KZ",
1280
+ "ground_truth": [
1281
+ {
1282
+ "tag": "EMAIL",
1283
+ "value": "Y1952@hotmail.com",
1284
+ "start": 76,
1285
+ "end": 93
1286
+ },
1287
+ {
1288
+ "tag": "IDCARDNUM",
1289
+ "value": "UB50272KZ",
1290
+ "start": 131,
1291
+ "end": 140
1292
+ }
1293
+ ],
1294
+ "predictions": []
1295
+ },
1296
+ {
1297
+ "source_text": "Path 1: Begin your journey at the Range Road 221 exhibit. Show your IJ8753370 to receive a stamp.",
1298
+ "ground_truth": [
1299
+ {
1300
+ "tag": "STREET",
1301
+ "value": "Range Road 221",
1302
+ "start": 34,
1303
+ "end": 48
1304
+ },
1305
+ {
1306
+ "tag": "PASSPORTNUM",
1307
+ "value": "IJ8753370",
1308
+ "start": 68,
1309
+ "end": 77
1310
+ }
1311
+ ],
1312
+ "predictions": []
1313
+ },
1314
+ {
1315
+ "source_text": "Dear Naphatsorn, I am reaching out to inquire about your sustainable living guides. As someone who is Female and 62 years old, I believe it's essential to live a sustainable lifestyle. Can I get more information about your guides?",
1316
+ "ground_truth": [
1317
+ {
1318
+ "tag": "GIVENNAME",
1319
+ "value": "Naphatsorn",
1320
+ "start": 5,
1321
+ "end": 15
1322
+ },
1323
+ {
1324
+ "tag": "GENDER",
1325
+ "value": "Female",
1326
+ "start": 102,
1327
+ "end": 108
1328
+ },
1329
+ {
1330
+ "tag": "AGE",
1331
+ "value": "62",
1332
+ "start": 113,
1333
+ "end": 115
1334
+ }
1335
+ ],
1336
+ "predictions": []
1337
+ },
1338
+ {
1339
+ "source_text": "The conversation was moderated by Gilvanete Charrada Caixeirinho, who ensured that all participants had an opportunity to share their thoughts and engage in a respectful and meaningful dialogue.",
1340
+ "ground_truth": [
1341
+ {
1342
+ "tag": "GIVENNAME",
1343
+ "value": "Gilvanete",
1344
+ "start": 34,
1345
+ "end": 43
1346
+ },
1347
+ {
1348
+ "tag": "SURNAME",
1349
+ "value": "Charrada Caixeirinho",
1350
+ "start": 44,
1351
+ "end": 64
1352
+ }
1353
+ ],
1354
+ "predictions": []
1355
+ },
1356
+ {
1357
+ "source_text": "Media Release and Permission Form - Sévrine Nakdali Sevciuc Bedöck grants permission to use images and recordings for promotional purposes.",
1358
+ "ground_truth": [
1359
+ {
1360
+ "tag": "GIVENNAME",
1361
+ "value": "Sévrine",
1362
+ "start": 36,
1363
+ "end": 43
1364
+ },
1365
+ {
1366
+ "tag": "SURNAME",
1367
+ "value": "Nakdali Sevciuc Bedöck",
1368
+ "start": 44,
1369
+ "end": 66
1370
+ }
1371
+ ],
1372
+ "predictions": []
1373
+ },
1374
+ {
1375
+ "source_text": "07:51:08 Menelaos Iouri to Chayanne: 'Hey, I need some help with designing a custom piece of jewelry for Sivalogini. I want it to represent our shared love of music.'",
1376
+ "ground_truth": [
1377
+ {
1378
+ "tag": "TIME",
1379
+ "value": "07:51:08",
1380
+ "start": 0,
1381
+ "end": 8
1382
+ },
1383
+ {
1384
+ "tag": "GIVENNAME",
1385
+ "value": "Menelaos Iouri",
1386
+ "start": 9,
1387
+ "end": 23
1388
+ },
1389
+ {
1390
+ "tag": "GIVENNAME",
1391
+ "value": "Chayanne",
1392
+ "start": 27,
1393
+ "end": 35
1394
+ },
1395
+ {
1396
+ "tag": "GIVENNAME",
1397
+ "value": "Sivalogini",
1398
+ "start": 105,
1399
+ "end": 115
1400
+ }
1401
+ ],
1402
+ "predictions": []
1403
+ },
1404
+ {
1405
+ "source_text": "I, Puya Niggler, acknowledge that I have read and understood the high-altitude travel agreement, including the risks associated with Pueblo at 64728.",
1406
+ "ground_truth": [
1407
+ {
1408
+ "tag": "GIVENNAME",
1409
+ "value": "Puya",
1410
+ "start": 3,
1411
+ "end": 7
1412
+ },
1413
+ {
1414
+ "tag": "SURNAME",
1415
+ "value": "Niggler",
1416
+ "start": 8,
1417
+ "end": 15
1418
+ },
1419
+ {
1420
+ "tag": "CITY",
1421
+ "value": "Pueblo",
1422
+ "start": 133,
1423
+ "end": 139
1424
+ },
1425
+ {
1426
+ "tag": "ZIPCODE",
1427
+ "value": "64728",
1428
+ "start": 143,
1429
+ "end": 148
1430
+ }
1431
+ ],
1432
+ "predictions": []
1433
+ },
1434
+ {
1435
+ "source_text": "11:42 Or Artrim: 'Our Mister team will be conducting a Kalagi workshop on 19/04/1986. All employees are encouraged to participate.'",
1436
+ "ground_truth": [
1437
+ {
1438
+ "tag": "TIME",
1439
+ "value": "11:42",
1440
+ "start": 0,
1441
+ "end": 5
1442
+ },
1443
+ {
1444
+ "tag": "GIVENNAME",
1445
+ "value": "Or Artrim",
1446
+ "start": 6,
1447
+ "end": 15
1448
+ },
1449
+ {
1450
+ "tag": "TITLE",
1451
+ "value": "Mister",
1452
+ "start": 22,
1453
+ "end": 28
1454
+ },
1455
+ {
1456
+ "tag": "CITY",
1457
+ "value": "Kalagi",
1458
+ "start": 55,
1459
+ "end": 61
1460
+ },
1461
+ {
1462
+ "tag": "DATE",
1463
+ "value": "19/04/1986",
1464
+ "start": 74,
1465
+ "end": 84
1466
+ }
1467
+ ],
1468
+ "predictions": []
1469
+ },
1470
+ {
1471
+ "source_text": "We require a valid form of identification for the literary awards. Could you please provide us with a copy of your 49097745338729 or 216169011?",
1472
+ "ground_truth": [
1473
+ {
1474
+ "tag": "IDCARDNUM",
1475
+ "value": "49097745338729",
1476
+ "start": 115,
1477
+ "end": 129
1478
+ },
1479
+ {
1480
+ "tag": "PASSPORTNUM",
1481
+ "value": "216169011",
1482
+ "start": 133,
1483
+ "end": 142
1484
+ }
1485
+ ],
1486
+ "predictions": []
1487
+ },
1488
+ {
1489
+ "source_text": "Azdren will be leading a workshop on warp-faced weave techniques, register by sending your +90.909-448.6913 and MS@aol.com.",
1490
+ "ground_truth": [
1491
+ {
1492
+ "tag": "GIVENNAME",
1493
+ "value": "Azdren",
1494
+ "start": 0,
1495
+ "end": 6
1496
+ },
1497
+ {
1498
+ "tag": "TELEPHONENUM",
1499
+ "value": "+90.909-448.6913",
1500
+ "start": 91,
1501
+ "end": 107
1502
+ },
1503
+ {
1504
+ "tag": "EMAIL",
1505
+ "value": "MS@aol.com",
1506
+ "start": 112,
1507
+ "end": 122
1508
+ }
1509
+ ],
1510
+ "predictions": []
1511
+ },
1512
+ {
1513
+ "source_text": "The next meeting for Ross area residents will be held at Love Creek Road 300.",
1514
+ "ground_truth": [
1515
+ {
1516
+ "tag": "CITY",
1517
+ "value": "Ross",
1518
+ "start": 21,
1519
+ "end": 25
1520
+ },
1521
+ {
1522
+ "tag": "STREET",
1523
+ "value": "Love Creek Road",
1524
+ "start": 57,
1525
+ "end": 72
1526
+ },
1527
+ {
1528
+ "tag": "BUILDINGNUM",
1529
+ "value": "300",
1530
+ "start": 73,
1531
+ "end": 76
1532
+ }
1533
+ ],
1534
+ "predictions": []
1535
+ },
1536
+ {
1537
+ "source_text": "Dear Atanaska Radhouan Anharalingam, we are excited to introduce our innovative energy solutions for apartments. Please fill out the attached form with your GJ@yahoo.com and +37.749306017 to learn more.",
1538
+ "ground_truth": [
1539
+ {
1540
+ "tag": "GIVENNAME",
1541
+ "value": "Atanaska Radhouan",
1542
+ "start": 5,
1543
+ "end": 22
1544
+ },
1545
+ {
1546
+ "tag": "SURNAME",
1547
+ "value": "Anharalingam",
1548
+ "start": 23,
1549
+ "end": 35
1550
+ },
1551
+ {
1552
+ "tag": "EMAIL",
1553
+ "value": "GJ@yahoo.com",
1554
+ "start": 157,
1555
+ "end": 169
1556
+ },
1557
+ {
1558
+ "tag": "TELEPHONENUM",
1559
+ "value": "+37.749306017",
1560
+ "start": 174,
1561
+ "end": 187
1562
+ }
1563
+ ],
1564
+ "predictions": []
1565
+ },
1566
+ {
1567
+ "source_text": "Attention all customers: Please be aware that we require a 010 29-809 8533 to contact you for order updates.",
1568
+ "ground_truth": [
1569
+ {
1570
+ "tag": "TELEPHONENUM",
1571
+ "value": "010 29-809 8533",
1572
+ "start": 59,
1573
+ "end": 74
1574
+ }
1575
+ ],
1576
+ "predictions": []
1577
+ },
1578
+ {
1579
+ "source_text": "(44)-1629.3769: Meet me at Cheltenham tomorrow for a astronomy convention. It's going to be a blast.",
1580
+ "ground_truth": [
1581
+ {
1582
+ "tag": "TELEPHONENUM",
1583
+ "value": "(44)-1629.3769",
1584
+ "start": 0,
1585
+ "end": 14
1586
+ },
1587
+ {
1588
+ "tag": "CITY",
1589
+ "value": "Cheltenham",
1590
+ "start": 27,
1591
+ "end": 37
1592
+ }
1593
+ ],
1594
+ "predictions": []
1595
+ },
1596
+ {
1597
+ "source_text": "Additional information on the Auditory Perception of Sonic Booms study is available at our office located at The Vineyard 20, Newark, LE12 7HH.",
1598
+ "ground_truth": [
1599
+ {
1600
+ "tag": "STREET",
1601
+ "value": "The Vineyard",
1602
+ "start": 109,
1603
+ "end": 121
1604
+ },
1605
+ {
1606
+ "tag": "BUILDINGNUM",
1607
+ "value": "20",
1608
+ "start": 122,
1609
+ "end": 124
1610
+ },
1611
+ {
1612
+ "tag": "CITY",
1613
+ "value": "Newark",
1614
+ "start": 126,
1615
+ "end": 132
1616
+ },
1617
+ {
1618
+ "tag": "ZIPCODE",
1619
+ "value": "LE12 7HH",
1620
+ "start": 134,
1621
+ "end": 142
1622
+ }
1623
+ ],
1624
+ "predictions": []
1625
+ },
1626
+ {
1627
+ "source_text": "How old is Loukian's child? We need to plan the folk dance moves accordingly.",
1628
+ "ground_truth": [
1629
+ {
1630
+ "tag": "GIVENNAME",
1631
+ "value": "Loukian",
1632
+ "start": 11,
1633
+ "end": 18
1634
+ }
1635
+ ],
1636
+ "predictions": []
1637
+ },
1638
+ {
1639
+ "source_text": "01:51 - reminder: Please remember to keep your yard free of clutter and noise as per our community bylaws.",
1640
+ "ground_truth": [
1641
+ {
1642
+ "tag": "TIME",
1643
+ "value": "01:51",
1644
+ "start": 0,
1645
+ "end": 5
1646
+ }
1647
+ ],
1648
+ "predictions": []
1649
+ },
1650
+ {
1651
+ "source_text": "Please contact Miss Kessi Kouanda for assistance.",
1652
+ "ground_truth": [
1653
+ {
1654
+ "tag": "TITLE",
1655
+ "value": "Miss",
1656
+ "start": 15,
1657
+ "end": 19
1658
+ },
1659
+ {
1660
+ "tag": "GIVENNAME",
1661
+ "value": "Kessi",
1662
+ "start": 20,
1663
+ "end": 25
1664
+ },
1665
+ {
1666
+ "tag": "SURNAME",
1667
+ "value": "Kouanda",
1668
+ "start": 26,
1669
+ "end": 33
1670
+ }
1671
+ ],
1672
+ "predictions": []
1673
+ },
1674
+ {
1675
+ "source_text": "Hello Madona, hope you're having a great day. I wanted to confirm our meeting at Kathotiya Road 426, Khanapur Parwaliya Sadak on 23/01/1993 to discuss the cartography project.",
1676
+ "ground_truth": [
1677
+ {
1678
+ "tag": "GIVENNAME",
1679
+ "value": "Madona",
1680
+ "start": 6,
1681
+ "end": 12
1682
+ },
1683
+ {
1684
+ "tag": "STREET",
1685
+ "value": "Kathotiya Road",
1686
+ "start": 81,
1687
+ "end": 95
1688
+ },
1689
+ {
1690
+ "tag": "BUILDINGNUM",
1691
+ "value": "426",
1692
+ "start": 96,
1693
+ "end": 99
1694
+ },
1695
+ {
1696
+ "tag": "CITY",
1697
+ "value": "Khanapur Parwaliya Sadak",
1698
+ "start": 101,
1699
+ "end": 125
1700
+ },
1701
+ {
1702
+ "tag": "DATE",
1703
+ "value": "23/01/1993",
1704
+ "start": 129,
1705
+ "end": 139
1706
+ }
1707
+ ],
1708
+ "predictions": []
1709
+ },
1710
+ {
1711
+ "source_text": "Jumana's Archery Equipment Inspection - 27/11/1941",
1712
+ "ground_truth": [
1713
+ {
1714
+ "tag": "GIVENNAME",
1715
+ "value": "Jumana",
1716
+ "start": 0,
1717
+ "end": 6
1718
+ },
1719
+ {
1720
+ "tag": "DATE",
1721
+ "value": "27/11/1941",
1722
+ "start": 40,
1723
+ "end": 50
1724
+ }
1725
+ ],
1726
+ "predictions": []
1727
+ },
1728
+ {
1729
+ "source_text": "Personal microclimate survey: What is your preferred air quality index, Simeon?",
1730
+ "ground_truth": [
1731
+ {
1732
+ "tag": "GIVENNAME",
1733
+ "value": "Simeon",
1734
+ "start": 72,
1735
+ "end": 78
1736
+ }
1737
+ ],
1738
+ "predictions": []
1739
+ },
1740
+ {
1741
+ "source_text": "El Trong Legler asked for advice on how to create a family tree, and Ramitha Sadeqi suggested using a service that requires a 692-826-6449 for verification.",
1742
+ "ground_truth": [
1743
+ {
1744
+ "tag": "GIVENNAME",
1745
+ "value": "El Trong",
1746
+ "start": 0,
1747
+ "end": 8
1748
+ },
1749
+ {
1750
+ "tag": "SURNAME",
1751
+ "value": "Legler",
1752
+ "start": 9,
1753
+ "end": 15
1754
+ },
1755
+ {
1756
+ "tag": "GIVENNAME",
1757
+ "value": "Ramitha",
1758
+ "start": 69,
1759
+ "end": 76
1760
+ },
1761
+ {
1762
+ "tag": "SURNAME",
1763
+ "value": "Sadeqi",
1764
+ "start": 77,
1765
+ "end": 83
1766
+ },
1767
+ {
1768
+ "tag": "SOCIALNUM",
1769
+ "value": "692-826-6449",
1770
+ "start": 126,
1771
+ "end": 138
1772
+ }
1773
+ ],
1774
+ "predictions": []
1775
+ },
1776
+ {
1777
+ "source_text": "Pasha Franklim: Hey Farha! My bonsai tree is dying, I need your help ASAP.",
1778
+ "ground_truth": [
1779
+ {
1780
+ "tag": "GIVENNAME",
1781
+ "value": "Pasha Franklim",
1782
+ "start": 0,
1783
+ "end": 14
1784
+ },
1785
+ {
1786
+ "tag": "GIVENNAME",
1787
+ "value": "Farha",
1788
+ "start": 20,
1789
+ "end": 25
1790
+ }
1791
+ ],
1792
+ "predictions": []
1793
+ },
1794
+ {
1795
+ "source_text": "I want to surprise Golnar on their birthday. Can you guys keep a secret?",
1796
+ "ground_truth": [
1797
+ {
1798
+ "tag": "GIVENNAME",
1799
+ "value": "Golnar",
1800
+ "start": 19,
1801
+ "end": 25
1802
+ }
1803
+ ],
1804
+ "predictions": []
1805
+ },
1806
+ {
1807
+ "source_text": "If you have any questions or would like to schedule a consultation, please don't hesitate to contact Eqrem at 0128 62 277 6657.",
1808
+ "ground_truth": [
1809
+ {
1810
+ "tag": "GIVENNAME",
1811
+ "value": "Eqrem",
1812
+ "start": 101,
1813
+ "end": 106
1814
+ },
1815
+ {
1816
+ "tag": "TELEPHONENUM",
1817
+ "value": "0128 62 277 6657",
1818
+ "start": 110,
1819
+ "end": 126
1820
+ }
1821
+ ],
1822
+ "predictions": []
1823
+ },
1824
+ {
1825
+ "source_text": "Hello Luningning, this is Delegate Klenger from the aquarium maintenance team. We need your 4340766747589394 to process your payment.",
1826
+ "ground_truth": [
1827
+ {
1828
+ "tag": "GIVENNAME",
1829
+ "value": "Luningning",
1830
+ "start": 6,
1831
+ "end": 16
1832
+ },
1833
+ {
1834
+ "tag": "TITLE",
1835
+ "value": "Delegate",
1836
+ "start": 26,
1837
+ "end": 34
1838
+ },
1839
+ {
1840
+ "tag": "SURNAME",
1841
+ "value": "Klenger",
1842
+ "start": 35,
1843
+ "end": 42
1844
+ },
1845
+ {
1846
+ "tag": "CREDITCARDNUMBER",
1847
+ "value": "4340766747589394",
1848
+ "start": 92,
1849
+ "end": 108
1850
+ }
1851
+ ],
1852
+ "predictions": []
1853
+ },
1854
+ {
1855
+ "source_text": "Exhibition Organizer : 'That sounds great Cornell Karthipan! Please fill out this form with your details: ID number: NP82IDQ3SK, birthdate: 13/12/1979, contact number: 06.85-04-19 29 and address: Meerut-Prayagraj Expressway 340, Mohanlal Ganj, 509324",
1856
+ "ground_truth": [
1857
+ {
1858
+ "tag": "GIVENNAME",
1859
+ "value": "Cornell Karthipan",
1860
+ "start": 42,
1861
+ "end": 59
1862
+ },
1863
+ {
1864
+ "tag": "IDCARDNUM",
1865
+ "value": "NP82IDQ3SK",
1866
+ "start": 117,
1867
+ "end": 127
1868
+ },
1869
+ {
1870
+ "tag": "DATE",
1871
+ "value": "13/12/1979",
1872
+ "start": 140,
1873
+ "end": 150
1874
+ },
1875
+ {
1876
+ "tag": "TELEPHONENUM",
1877
+ "value": "06.85-04-19 29",
1878
+ "start": 168,
1879
+ "end": 182
1880
+ },
1881
+ {
1882
+ "tag": "STREET",
1883
+ "value": "Meerut-Prayagraj Expressway",
1884
+ "start": 196,
1885
+ "end": 223
1886
+ },
1887
+ {
1888
+ "tag": "BUILDINGNUM",
1889
+ "value": "340",
1890
+ "start": 224,
1891
+ "end": 227
1892
+ },
1893
+ {
1894
+ "tag": "CITY",
1895
+ "value": "Mohanlal Ganj",
1896
+ "start": 229,
1897
+ "end": 242
1898
+ },
1899
+ {
1900
+ "tag": "ZIPCODE",
1901
+ "value": "509324",
1902
+ "start": 244,
1903
+ "end": 250
1904
+ }
1905
+ ],
1906
+ "predictions": []
1907
+ },
1908
+ {
1909
+ "source_text": "New task assigned to Samaher: Update the 1904 and V0B for the upcoming event.",
1910
+ "ground_truth": [
1911
+ {
1912
+ "tag": "GIVENNAME",
1913
+ "value": "Samaher",
1914
+ "start": 21,
1915
+ "end": 28
1916
+ },
1917
+ {
1918
+ "tag": "BUILDINGNUM",
1919
+ "value": "1904",
1920
+ "start": 41,
1921
+ "end": 45
1922
+ },
1923
+ {
1924
+ "tag": "ZIPCODE",
1925
+ "value": "V0B",
1926
+ "start": 50,
1927
+ "end": 53
1928
+ }
1929
+ ],
1930
+ "predictions": []
1931
+ },
1932
+ {
1933
+ "source_text": "Maybe reach out to Caridad Lesia, perhaps we can set up a meeting with the ancestors of Stäger-von Allmen van Oerle?",
1934
+ "ground_truth": [
1935
+ {
1936
+ "tag": "GIVENNAME",
1937
+ "value": "Caridad Lesia",
1938
+ "start": 19,
1939
+ "end": 32
1940
+ },
1941
+ {
1942
+ "tag": "SURNAME",
1943
+ "value": "Stäger-von Allmen van Oerle",
1944
+ "start": 88,
1945
+ "end": 115
1946
+ }
1947
+ ],
1948
+ "predictions": []
1949
+ },
1950
+ {
1951
+ "source_text": "The following individuals have contributed to this project: Blenda Stoia, Elycia Kirchmayr Losmaz, and Gasser Ethanaël Dutranoy.",
1952
+ "ground_truth": [
1953
+ {
1954
+ "tag": "GIVENNAME",
1955
+ "value": "Blenda",
1956
+ "start": 60,
1957
+ "end": 66
1958
+ },
1959
+ {
1960
+ "tag": "SURNAME",
1961
+ "value": "Stoia",
1962
+ "start": 67,
1963
+ "end": 72
1964
+ },
1965
+ {
1966
+ "tag": "GIVENNAME",
1967
+ "value": "Elycia",
1968
+ "start": 74,
1969
+ "end": 80
1970
+ },
1971
+ {
1972
+ "tag": "SURNAME",
1973
+ "value": "Kirchmayr Losmaz",
1974
+ "start": 81,
1975
+ "end": 97
1976
+ },
1977
+ {
1978
+ "tag": "GIVENNAME",
1979
+ "value": "Gasser Ethanaël",
1980
+ "start": 103,
1981
+ "end": 118
1982
+ },
1983
+ {
1984
+ "tag": "SURNAME",
1985
+ "value": "Dutranoy",
1986
+ "start": 119,
1987
+ "end": 127
1988
+ }
1989
+ ],
1990
+ "predictions": []
1991
+ },
1992
+ {
1993
+ "source_text": "Enjoying the satirical poems of Jianchao Scrivano. Great perspectives.",
1994
+ "ground_truth": [
1995
+ {
1996
+ "tag": "GIVENNAME",
1997
+ "value": "Jianchao",
1998
+ "start": 32,
1999
+ "end": 40
2000
+ },
2001
+ {
2002
+ "tag": "SURNAME",
2003
+ "value": "Scrivano",
2004
+ "start": 41,
2005
+ "end": 49
2006
+ }
2007
+ ],
2008
+ "predictions": []
2009
+ },
2010
+ {
2011
+ "source_text": "Dear puzzle enthusiasts, this is a reminder to RSVP to our event with your BA@gmail.com address.",
2012
+ "ground_truth": [
2013
+ {
2014
+ "tag": "EMAIL",
2015
+ "value": "BA@gmail.com",
2016
+ "start": 75,
2017
+ "end": 87
2018
+ }
2019
+ ],
2020
+ "predictions": []
2021
+ },
2022
+ {
2023
+ "source_text": "The conversation is about the educational journey of Giusva in linguistics and semiotics.",
2024
+ "ground_truth": [
2025
+ {
2026
+ "tag": "GIVENNAME",
2027
+ "value": "Giusva",
2028
+ "start": 53,
2029
+ "end": 59
2030
+ }
2031
+ ],
2032
+ "predictions": []
2033
+ },
2034
+ {
2035
+ "source_text": "Caylan François-Joseph: 'I have it, 1996NC@aol.com me and I'll send it over'",
2036
+ "ground_truth": [
2037
+ {
2038
+ "tag": "GIVENNAME",
2039
+ "value": "Caylan François-Joseph",
2040
+ "start": 0,
2041
+ "end": 22
2042
+ },
2043
+ {
2044
+ "tag": "EMAIL",
2045
+ "value": "1996NC@aol.com",
2046
+ "start": 36,
2047
+ "end": 50
2048
+ }
2049
+ ],
2050
+ "predictions": []
2051
+ },
2052
+ {
2053
+ "source_text": "Min Joanny is the one helping me with this task.",
2054
+ "ground_truth": [
2055
+ {
2056
+ "tag": "TITLE",
2057
+ "value": "Min",
2058
+ "start": 0,
2059
+ "end": 3
2060
+ },
2061
+ {
2062
+ "tag": "GIVENNAME",
2063
+ "value": "Joanny",
2064
+ "start": 4,
2065
+ "end": 10
2066
+ }
2067
+ ],
2068
+ "predictions": []
2069
+ },
2070
+ {
2071
+ "source_text": "The Form Fill report for Sadya Laurelli contains 783451229592 and 404880038.",
2072
+ "ground_truth": [
2073
+ {
2074
+ "tag": "GIVENNAME",
2075
+ "value": "Sadya",
2076
+ "start": 25,
2077
+ "end": 30
2078
+ },
2079
+ {
2080
+ "tag": "SURNAME",
2081
+ "value": "Laurelli",
2082
+ "start": 31,
2083
+ "end": 39
2084
+ },
2085
+ {
2086
+ "tag": "IDCARDNUM",
2087
+ "value": "783451229592",
2088
+ "start": 49,
2089
+ "end": 61
2090
+ },
2091
+ {
2092
+ "tag": "PASSPORTNUM",
2093
+ "value": "404880038",
2094
+ "start": 66,
2095
+ "end": 75
2096
+ }
2097
+ ],
2098
+ "predictions": []
2099
+ },
2100
+ {
2101
+ "source_text": "We recommend wearing comfortable shoes and bringing a Male-friendly water bottle. The event will take place regardless of the 2:44 weather.",
2102
+ "ground_truth": [
2103
+ {
2104
+ "tag": "GENDER",
2105
+ "value": "Male",
2106
+ "start": 54,
2107
+ "end": 58
2108
+ },
2109
+ {
2110
+ "tag": "TIME",
2111
+ "value": "2:44",
2112
+ "start": 126,
2113
+ "end": 130
2114
+ }
2115
+ ],
2116
+ "predictions": []
2117
+ },
2118
+ {
2119
+ "source_text": "Zufferey Gutenhan Morella is looking for inspiration for their next Mountain Whisper Diaries project.",
2120
+ "ground_truth": [
2121
+ {
2122
+ "tag": "SURNAME",
2123
+ "value": "Zufferey Gutenhan Morella",
2124
+ "start": 0,
2125
+ "end": 25
2126
+ }
2127
+ ],
2128
+ "predictions": []
2129
+ }
2130
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99b59a4bff78d01c8159fdf24bff68c1f06d10f851bf7f25162c3b6ed14a6ad
3
+ size 741417103
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "local_files_only": false,
15
+ "mask_token": "[MASK]",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "[PAD]",
18
+ "sep_token": "[SEP]",
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }