Upload folder using huggingface_hub

ai4privacy/SpanBased-CustomDeBERTa/classification_report.json

@@ -0,0 +1,128 @@
+{
+  "AGE": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 4
+  },
+  "BUILDINGNUM": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 8
+  },
+  "CITY": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 21
+  },
+  "CREDITCARDNUMBER": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 2
+  },
+  "DATE": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 16
+  },
+  "DRIVERLICENSENUM": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 1
+  },
+  "EMAIL": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 10
+  },
+  "GENDER": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 3
+  },
+  "GIVENNAME": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 91
+  },
+  "IDCARDNUM": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 11
+  },
+  "PASSPORTNUM": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 4
+  },
+  "SOCIALNUM": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 5
+  },
+  "STREET": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 10
+  },
+  "SURNAME": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 35
+  },
+  "TELEPHONENUM": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 13
+  },
+  "TIME": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 12
+  },
+  "TITLE": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 8
+  },
+  "ZIPCODE": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 9
+  },
+  "OVERALL_MICRO": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 263
+  },
+  "OVERALL_MACRO": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 263
+  },
+  "OVERALL_WEIGHTED": {
+    "precision": 0.0,
+    "recall": 0.0,
+    "f1-score": 0.0,
+    "support": 263
+  }
+}

ai4privacy/SpanBased-CustomDeBERTa/config.json

@@ -0,0 +1,79 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "AGE",
+    "2": "BUILDINGNUM",
+    "3": "CITY",
+    "4": "CREDITCARDNUMBER",
+    "5": "DATE",
+    "6": "DRIVERLICENSENUM",
+    "7": "EMAIL",
+    "8": "GENDER",
+    "9": "GIVENNAME",
+    "10": "IDCARDNUM",
+    "11": "PASSPORTNUM",
+    "12": "SOCIALNUM",
+    "13": "STREET",
+    "14": "SURNAME",
+    "15": "TAXNUM",
+    "16": "TELEPHONENUM",
+    "17": "TIME",
+    "18": "TITLE",
+    "19": "ZIPCODE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AGE": 1,
+    "BUILDINGNUM": 2,
+    "CITY": 3,
+    "CREDITCARDNUMBER": 4,
+    "DATE": 5,
+    "DRIVERLICENSENUM": 6,
+    "EMAIL": 7,
+    "GENDER": 8,
+    "GIVENNAME": 9,
+    "IDCARDNUM": 10,
+    "O": 0,
+    "PASSPORTNUM": 11,
+    "SOCIALNUM": 12,
+    "STREET": 13,
+    "SURNAME": 14,
+    "TAXNUM": 15,
+    "TELEPHONENUM": 16,
+    "TIME": 17,
+    "TITLE": 18,
+    "ZIPCODE": 19
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 384,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0.0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

ai4privacy/SpanBased-CustomDeBERTa/predictions.json

@@ -0,0 +1,2178 @@
+[
+  {
+    "source_text": "Dittmer Subsom has created a to-do list for the fitness routine: 08/08/1942 - cardio, 01/03/1939 - strength training.",
+    "ground_truth": [
+      {
+        "tag": "SURNAME",
+        "value": "Dittmer Subsom",
+        "start": 0,
+        "end": 14
+      },
+      {
+        "tag": "DATE",
+        "value": "08/08/1942",
+        "start": 65,
+        "end": 75
+      },
+      {
+        "tag": "DATE",
+        "value": "01/03/1939",
+        "start": 86,
+        "end": 96
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "El Trong",
+        "start": 0,
+        "end": 8
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Legler",
+        "start": 9,
+        "end": 15
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Ramitha",
+        "start": 69,
+        "end": 76
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Sadeqi",
+        "start": 77,
+        "end": 83
+      },
+      {
+        "tag": "SOCIALNUM",
+        "value": "692-826-6449",
+        "start": 126,
+        "end": 138
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "01:17:17 Qilin Sibi: 'Hey, does anyone have Madame's contact info?'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "01:17:17",
+        "start": 0,
+        "end": 8
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Qilin Sibi",
+        "start": 9,
+        "end": 19
+      },
+      {
+        "tag": "TITLE",
+        "value": "Madame",
+        "start": 44,
+        "end": 50
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Dear Fetih, your application for the space simulation programme has been accepted. Please find the attached document for further details.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Fetih",
+        "start": 5,
+        "end": 10
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Free Public Wi-Fi Hotspots in Wabush",
+    "ground_truth": [
+      {
+        "tag": "CITY",
+        "value": "Wabush",
+        "start": 30,
+        "end": 36
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "FI@gmail.com sent a request for a to-do list on woodworking tools.",
+    "ground_truth": [
+      {
+        "tag": "EMAIL",
+        "value": "FI@gmail.com",
+        "start": 0,
+        "end": 12
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Palzom",
+        "start": 184,
+        "end": 190
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Application for Thrift Store Seasonal Display: Arvi",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Arvi",
+        "start": 47,
+        "end": 51
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Dénise Dänger, Your (183)-6397735 has been registered as the contact number for the solar charging station setup.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Dénise",
+        "start": 0,
+        "end": 6
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Dänger",
+        "start": 7,
+        "end": 13
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "(183)-6397735",
+        "start": 20,
+        "end": 33
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Starr",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "CITY",
+        "value": "Duncan",
+        "start": 35,
+        "end": 41
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "G6G 0A1",
+        "start": 68,
+        "end": 75
+      },
+      {
+        "tag": "PASSPORTNUM",
+        "value": "QS8186071",
+        "start": 101,
+        "end": 110
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "...",
+    "ground_truth": [],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Deni",
+        "start": 3,
+        "end": 7
+      },
+      {
+        "tag": "DATE",
+        "value": "22/02/2013",
+        "start": 120,
+        "end": 130
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "00.7011-7742 received an alert for a rural exploration diary entry at Greatham Road (114 - 118)",
+    "ground_truth": [
+      {
+        "tag": "TELEPHONENUM",
+        "value": "00.7011-7742",
+        "start": 0,
+        "end": 12
+      },
+      {
+        "tag": "STREET",
+        "value": "Greatham Road",
+        "start": 70,
+        "end": 83
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "(114 - 118)",
+        "start": 84,
+        "end": 95
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Hi Keita Natacha, I need your KH86840VN to validate your identity.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Keita Natacha",
+        "start": 3,
+        "end": 16
+      },
+      {
+        "tag": "IDCARDNUM",
+        "value": "KH86840VN",
+        "start": 30,
+        "end": 39
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Congratulations to Salvadora Kupf Otgonbaatar on winning the MVP award! Your gift card will be sent to Emsley Drive 74117",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Salvadora",
+        "start": 19,
+        "end": 28
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Kupf Otgonbaatar",
+        "start": 29,
+        "end": 45
+      },
+      {
+        "tag": "STREET",
+        "value": "Emsley Drive",
+        "start": 103,
+        "end": 115
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "74117",
+        "start": 116,
+        "end": 121
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "The bylaws require that all members provide their C5MSDGU8FC and T@aol.com.",
+    "ground_truth": [
+      {
+        "tag": "IDCARDNUM",
+        "value": "C5MSDGU8FC",
+        "start": 50,
+        "end": 60
+      },
+      {
+        "tag": "EMAIL",
+        "value": "T@aol.com",
+        "start": 65,
+        "end": 74
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Form fill: Salvia's address is Veerasagara Main Road 2978, Ghatanji Rajendranagar",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Salvia",
+        "start": 11,
+        "end": 17
+      },
+      {
+        "tag": "STREET",
+        "value": "Veerasagara Main Road",
+        "start": 31,
+        "end": 52
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "2978",
+        "start": 53,
+        "end": 57
+      },
+      {
+        "tag": "CITY",
+        "value": "Ghatanji Rajendranagar",
+        "start": 59,
+        "end": 81
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Darrin Lingnardz Bakri's Climate Adaptation Measures: 0228141741",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Darrin",
+        "start": 0,
+        "end": 6
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Lingnardz Bakri",
+        "start": 7,
+        "end": 22
+      },
+      {
+        "tag": "SOCIALNUM",
+        "value": "0228141741",
+        "start": 54,
+        "end": 64
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "To finalize your citizenship application, please submit a copy of your OU6758730, CDBSROOFJA, and 8061505243.",
+    "ground_truth": [
+      {
+        "tag": "PASSPORTNUM",
+        "value": "OU6758730",
+        "start": 71,
+        "end": 80
+      },
+      {
+        "tag": "IDCARDNUM",
+        "value": "CDBSROOFJA",
+        "start": 82,
+        "end": 92
+      },
+      {
+        "tag": "SOCIALNUM",
+        "value": "8061505243",
+        "start": 98,
+        "end": 108
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "...",
+    "ground_truth": [],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Aberash Bajrishe",
+        "start": 6,
+        "end": 22
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Cosmadopoulos",
+        "start": 23,
+        "end": 36
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Sulayman",
+        "start": 41,
+        "end": 49
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Lorenzon",
+        "start": 50,
+        "end": 58
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Renu",
+        "start": 110,
+        "end": 114
+      },
+      {
+        "tag": "CITY",
+        "value": "Roosevelt",
+        "start": 272,
+        "end": 281
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Lorikë will ensure that the treehouse is designed with sustainable materials and meets the 32 building codes.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Lorikë",
+        "start": 0,
+        "end": 6
+      },
+      {
+        "tag": "AGE",
+        "value": "32",
+        "start": 91,
+        "end": 93
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Please welcome Aran to the team.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Aran",
+        "start": 15,
+        "end": 19
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Ombeline Roxie",
+        "start": 3,
+        "end": 17
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Nedzip",
+        "start": 152,
+        "end": 158
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Jianying",
+        "start": 21,
+        "end": 29
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "+4.99-415 9321",
+        "start": 72,
+        "end": 86
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Attached is the form filled by Hedia Çevikoguz for charity involvement record purposes.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Hedia",
+        "start": 31,
+        "end": 36
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Çevikoguz",
+        "start": 37,
+        "end": 46
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Subscription confirmation for Narjisse Migot on our newsletter: Medieval Garden Digest",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Narjisse",
+        "start": 30,
+        "end": 38
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Migot",
+        "start": 39,
+        "end": 44
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Please provide your ZKSO2WCDUM and 4087818840 for verification purposes.",
+    "ground_truth": [
+      {
+        "tag": "IDCARDNUM",
+        "value": "ZKSO2WCDUM",
+        "start": 20,
+        "end": 30
+      },
+      {
+        "tag": "SOCIALNUM",
+        "value": "4087818840",
+        "start": 35,
+        "end": 45
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "During our family reunion, we'll be discussing our shared Ravikamatham Dahej roots and ancestry.",
+    "ground_truth": [
+      {
+        "tag": "CITY",
+        "value": "Ravikamatham Dahej",
+        "start": 58,
+        "end": 76
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Hadie Mayada Newatu: Yeah, that's fine. The more the merrier!",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Hadie Mayada",
+        "start": 0,
+        "end": 12
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Newatu",
+        "start": 13,
+        "end": 19
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Please submit your comments on the expansion plan to Z@yahoo.com by 25/09/1959.",
+    "ground_truth": [
+      {
+        "tag": "EMAIL",
+        "value": "Z@yahoo.com",
+        "start": 53,
+        "end": 64
+      },
+      {
+        "tag": "DATE",
+        "value": "25/09/1959",
+        "start": 68,
+        "end": 78
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Jovanna Folasade",
+        "start": 0,
+        "end": 16
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Glomb",
+        "start": 17,
+        "end": 22
+      },
+      {
+        "tag": "CITY",
+        "value": "Saint-Henri-de-Lévis",
+        "start": 120,
+        "end": 140
+      },
+      {
+        "tag": "STREET",
+        "value": "4th Line",
+        "start": 158,
+        "end": 166
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Please confirm your availability for the meeting on 27/07/2010 at 00:17:49.",
+    "ground_truth": [
+      {
+        "tag": "DATE",
+        "value": "27/07/2010",
+        "start": 52,
+        "end": 62
+      },
+      {
+        "tag": "TIME",
+        "value": "00:17:49",
+        "start": 66,
+        "end": 74
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Merry Christmas, Herminie Muhaber! 🎅",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Herminie Muhaber",
+        "start": 17,
+        "end": 33
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Looking for job training programs? We have openings in Datil.",
+    "ground_truth": [
+      {
+        "tag": "CITY",
+        "value": "Datil",
+        "start": 55,
+        "end": 60
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Our office is located at Trinidad Drive 1386, Backus, 64130.",
+    "ground_truth": [
+      {
+        "tag": "STREET",
+        "value": "Trinidad Drive",
+        "start": 25,
+        "end": 39
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "1386",
+        "start": 40,
+        "end": 44
+      },
+      {
+        "tag": "CITY",
+        "value": "Backus",
+        "start": 46,
+        "end": 52
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "64130",
+        "start": 54,
+        "end": 59
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Wenliang's poetry is not just written words, but artistry on parchment.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Wenliang",
+        "start": 0,
+        "end": 8
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Eloïc Sofyan shared a file 'Ring Design Sketches2.zip': Here is the updated design concept for Silvère Abdeladim's ring.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Eloïc Sofyan",
+        "start": 0,
+        "end": 12
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Silvère Abdeladim",
+        "start": 95,
+        "end": 112
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Edmar has 349734576006955 and 47230 for delivery)",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Edmar",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "CREDITCARDNUMBER",
+        "value": "349734576006955",
+        "start": 10,
+        "end": 25
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "47230",
+        "start": 30,
+        "end": 35
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "As part of the cultural exchange program, Stanzl will be staying with a host family in Delta.",
+    "ground_truth": [
+      {
+        "tag": "SURNAME",
+        "value": "Stanzl",
+        "start": 42,
+        "end": 48
+      },
+      {
+        "tag": "CITY",
+        "value": "Delta",
+        "start": 87,
+        "end": 92
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "480-08-2001 reported a Female 3 bear in the Arvada Lamar Heights area.",
+    "ground_truth": [
+      {
+        "tag": "SOCIALNUM",
+        "value": "480-08-2001",
+        "start": 0,
+        "end": 11
+      },
+      {
+        "tag": "GENDER",
+        "value": "Female",
+        "start": 23,
+        "end": 29
+      },
+      {
+        "tag": "AGE",
+        "value": "3",
+        "start": 30,
+        "end": 31
+      },
+      {
+        "tag": "CITY",
+        "value": "Arvada Lamar Heights",
+        "start": 44,
+        "end": 64
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "11/11/1949 - Interoffice Correspondence: Alojzija Cernoch Fivet has been awarded the 'Most Improved Player' award in the gellyball tournament.",
+    "ground_truth": [
+      {
+        "tag": "DATE",
+        "value": "11/11/1949",
+        "start": 0,
+        "end": 10
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Alojzija",
+        "start": 41,
+        "end": 49
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Cernoch Fivet",
+        "start": 50,
+        "end": 63
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Enilda Emelone's diary entry 29/01/1991: Successfully brewed 305814 IPA using Todapur Inner Road hops.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Enilda",
+        "start": 0,
+        "end": 6
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Emelone",
+        "start": 7,
+        "end": 14
+      },
+      {
+        "tag": "DATE",
+        "value": "29/01/1991",
+        "start": 29,
+        "end": 39
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "305814",
+        "start": 61,
+        "end": 67
+      },
+      {
+        "tag": "STREET",
+        "value": "Todapur Inner Road",
+        "start": 78,
+        "end": 96
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "The league administrator, Alihan Eloan, has announced a new policy regarding player conduct.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Alihan Eloan",
+        "start": 26,
+        "end": 38
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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?'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "10:42",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Amina",
+        "start": 6,
+        "end": 11
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Hazbije",
+        "start": 18,
+        "end": 25
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Nejc Gavin has written a poem for Nepa's birthday on 27/05/2010.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Nejc Gavin",
+        "start": 0,
+        "end": 10
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Nepa",
+        "start": 34,
+        "end": 38
+      },
+      {
+        "tag": "DATE",
+        "value": "27/05/2010",
+        "start": 53,
+        "end": 63
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "16:42 Aomar: 'Hey Dilbrin, I loved your anti-gravity basket weaving design at the Dartmouth workshop.'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "16:42",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Aomar",
+        "start": 6,
+        "end": 11
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Dilbrin",
+        "start": 18,
+        "end": 25
+      },
+      {
+        "tag": "CITY",
+        "value": "Dartmouth",
+        "start": 82,
+        "end": 91
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Üsame Sivagnanasuntharam Moehr: Can we get an update on the seasonal updates memos?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Üsame",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Sivagnanasuntharam Moehr",
+        "start": 6,
+        "end": 30
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Daymon",
+        "start": 23,
+        "end": 29
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Dizara Valquiria",
+        "start": 111,
+        "end": 127
+      },
+      {
+        "tag": "DATE",
+        "value": "18/04/1967",
+        "start": 130,
+        "end": 140
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "quarter past 1",
+        "start": 0,
+        "end": 14
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Neya",
+        "start": 15,
+        "end": 19
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Erduan Kenin",
+        "start": 67,
+        "end": 79
+      },
+      {
+        "tag": "SURNAME",
+        "value": "D'albora",
+        "start": 80,
+        "end": 88
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Dear Elijon Zabedin Qalandari Sikiric, please find attached your Space Simulation Participation Records. Your participant ID is VD76923JJ.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Elijon Zabedin",
+        "start": 5,
+        "end": 19
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Qalandari Sikiric",
+        "start": 20,
+        "end": 37
+      },
+      {
+        "tag": "IDCARDNUM",
+        "value": "VD76923JJ",
+        "start": 128,
+        "end": 137
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "04:18 Shanaz: 'Looking forward to the Hepburn performance on 26/07/1944'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "04:18",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Shanaz",
+        "start": 6,
+        "end": 12
+      },
+      {
+        "tag": "CITY",
+        "value": "Hepburn",
+        "start": 38,
+        "end": 45
+      },
+      {
+        "tag": "DATE",
+        "value": "26/07/1944",
+        "start": 61,
+        "end": 71
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Ivanice",
+        "start": 3,
+        "end": 10
+      },
+      {
+        "tag": "AGE",
+        "value": "17",
+        "start": 137,
+        "end": 139
+      },
+      {
+        "tag": "GENDER",
+        "value": "F",
+        "start": 144,
+        "end": 145
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "7:06:16 PM Jesco Nahum Gennai: 'Good morning, my name is Dicle Pogue. I'm here to facilitate the group.'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "7:06:16 PM",
+        "start": 0,
+        "end": 10
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Jesco Nahum",
+        "start": 11,
+        "end": 22
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Gennai",
+        "start": 23,
+        "end": 29
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Dicle",
+        "start": 57,
+        "end": 62
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Pogue",
+        "start": 63,
+        "end": 68
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Jodie",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Hilf Passafiume",
+        "start": 6,
+        "end": 21
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "091-128.3183",
+        "start": 137,
+        "end": 149
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "I'm sending over our suggested integration designs to your M@aol.com with attachments.",
+    "ground_truth": [
+      {
+        "tag": "EMAIL",
+        "value": "M@aol.com",
+        "start": 59,
+        "end": 68
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Srbislava",
+        "start": 3,
+        "end": 12
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "+4454712-0464",
+        "start": 142,
+        "end": 155
+      },
+      {
+        "tag": "EMAIL",
+        "value": "evguetinella@gmail.com",
+        "start": 159,
+        "end": 181
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Skybound with Orestina Zizë at the Shahapur Gatarad Village kite festival",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Orestina Zizë",
+        "start": 14,
+        "end": 27
+      },
+      {
+        "tag": "CITY",
+        "value": "Shahapur Gatarad Village",
+        "start": 35,
+        "end": 59
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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...'",
+    "ground_truth": [
+      {
+        "tag": "TELEPHONENUM",
+        "value": "+3.036-244 1257",
+        "start": 0,
+        "end": 15
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "All residents (Everest Leonas Benguella) are required to provide government issued ID (6283734972251 or E570912132781) for verification.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Everest Leonas",
+        "start": 15,
+        "end": 29
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Benguella",
+        "start": 30,
+        "end": 39
+      },
+      {
+        "tag": "IDCARDNUM",
+        "value": "6283734972251",
+        "start": 87,
+        "end": 100
+      },
+      {
+        "tag": "DRIVERLICENSENUM",
+        "value": "E570912132781",
+        "start": 104,
+        "end": 117
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Happy birthday to Vrona! Hope you have a fantastic day.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Vrona",
+        "start": 18,
+        "end": 23
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Contact Cataleya at +288 08.694.6514 to participate in Ofc",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Cataleya",
+        "start": 8,
+        "end": 16
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "+288 08.694.6514",
+        "start": 20,
+        "end": 36
+      },
+      {
+        "tag": "TITLE",
+        "value": "Ofc",
+        "start": 55,
+        "end": 58
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Monitoring Log #TPQ321B72K: At 7:39 on October 22nd, 1962, Woody Skarzynski measured the water quality parameters in the nearby wetlands.",
+    "ground_truth": [
+      {
+        "tag": "IDCARDNUM",
+        "value": "TPQ321B72K",
+        "start": 16,
+        "end": 26
+      },
+      {
+        "tag": "TIME",
+        "value": "7:39",
+        "start": 31,
+        "end": 35
+      },
+      {
+        "tag": "DATE",
+        "value": "October 22nd, 1962",
+        "start": 39,
+        "end": 57
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Woody",
+        "start": 59,
+        "end": 64
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Skarzynski",
+        "start": 65,
+        "end": 75
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Noely Henrieta",
+        "start": 17,
+        "end": 31
+      },
+      {
+        "tag": "DATE",
+        "value": "28th March 2023",
+        "start": 110,
+        "end": 125
+      },
+      {
+        "tag": "EMAIL",
+        "value": "mescholt@aol.com",
+        "start": 129,
+        "end": 145
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Please review the attached education plan and confirm your Dodo and SA50045VL for verification.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Dodo",
+        "start": 59,
+        "end": 63
+      },
+      {
+        "tag": "IDCARDNUM",
+        "value": "SA50045VL",
+        "start": 68,
+        "end": 77
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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",
+    "ground_truth": [
+      {
+        "tag": "EMAIL",
+        "value": "Y1952@hotmail.com",
+        "start": 76,
+        "end": 93
+      },
+      {
+        "tag": "IDCARDNUM",
+        "value": "UB50272KZ",
+        "start": 131,
+        "end": 140
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "7:42:51 PM Kolia Joas: 'Hey did you vote in the Mandvi Taluka election?'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "7:42:51 PM",
+        "start": 0,
+        "end": 10
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Kolia Joas",
+        "start": 11,
+        "end": 21
+      },
+      {
+        "tag": "CITY",
+        "value": "Mandvi Taluka",
+        "start": 48,
+        "end": 61
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Naphatsorn",
+        "start": 5,
+        "end": 15
+      },
+      {
+        "tag": "GENDER",
+        "value": "Female",
+        "start": 102,
+        "end": 108
+      },
+      {
+        "tag": "AGE",
+        "value": "62",
+        "start": 113,
+        "end": 115
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Gilvanete",
+        "start": 34,
+        "end": 43
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Charrada Caixeirinho",
+        "start": 44,
+        "end": 64
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Community education session attendees, please note that your Shiyara and Leese will be shared with the organizers.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Shiyara",
+        "start": 61,
+        "end": 68
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Leese",
+        "start": 73,
+        "end": 78
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "07:51:08",
+        "start": 0,
+        "end": 8
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Menelaos Iouri",
+        "start": 9,
+        "end": 23
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Chayanne",
+        "start": 27,
+        "end": 35
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Sivalogini",
+        "start": 105,
+        "end": 115
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Puya",
+        "start": 3,
+        "end": 7
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Niggler",
+        "start": 8,
+        "end": 15
+      },
+      {
+        "tag": "CITY",
+        "value": "Pueblo",
+        "start": 133,
+        "end": 139
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "64728",
+        "start": 143,
+        "end": 148
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "11:42",
+        "start": 0,
+        "end": 5
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Or Artrim",
+        "start": 6,
+        "end": 15
+      },
+      {
+        "tag": "TITLE",
+        "value": "Mister",
+        "start": 22,
+        "end": 28
+      },
+      {
+        "tag": "CITY",
+        "value": "Kalagi",
+        "start": 55,
+        "end": 61
+      },
+      {
+        "tag": "DATE",
+        "value": "19/04/1986",
+        "start": 74,
+        "end": 84
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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?",
+    "ground_truth": [
+      {
+        "tag": "IDCARDNUM",
+        "value": "49097745338729",
+        "start": 115,
+        "end": 129
+      },
+      {
+        "tag": "PASSPORTNUM",
+        "value": "216169011",
+        "start": 133,
+        "end": 142
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Azdren",
+        "start": 0,
+        "end": 6
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "+90.909-448.6913",
+        "start": 91,
+        "end": 107
+      },
+      {
+        "tag": "EMAIL",
+        "value": "MS@aol.com",
+        "start": 112,
+        "end": 122
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "The next meeting for Ross area residents will be held at Love Creek Road 300.",
+    "ground_truth": [
+      {
+        "tag": "CITY",
+        "value": "Ross",
+        "start": 21,
+        "end": 25
+      },
+      {
+        "tag": "STREET",
+        "value": "Love Creek Road",
+        "start": 57,
+        "end": 72
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "300",
+        "start": 73,
+        "end": 76
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Atanaska Radhouan",
+        "start": 5,
+        "end": 22
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Anharalingam",
+        "start": 23,
+        "end": 35
+      },
+      {
+        "tag": "EMAIL",
+        "value": "GJ@yahoo.com",
+        "start": 157,
+        "end": 169
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "+37.749306017",
+        "start": 174,
+        "end": 187
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Attention all customers: Please be aware that we require a 010 29-809 8533 to contact you for order updates.",
+    "ground_truth": [
+      {
+        "tag": "TELEPHONENUM",
+        "value": "010 29-809 8533",
+        "start": 59,
+        "end": 74
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "(44)-1629.3769: Meet me at Cheltenham tomorrow for a astronomy convention. It's going to be a blast.",
+    "ground_truth": [
+      {
+        "tag": "TELEPHONENUM",
+        "value": "(44)-1629.3769",
+        "start": 0,
+        "end": 14
+      },
+      {
+        "tag": "CITY",
+        "value": "Cheltenham",
+        "start": 27,
+        "end": 37
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "STREET",
+        "value": "The Vineyard",
+        "start": 109,
+        "end": 121
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "20",
+        "start": 122,
+        "end": 124
+      },
+      {
+        "tag": "CITY",
+        "value": "Newark",
+        "start": 126,
+        "end": 132
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "LE12 7HH",
+        "start": 134,
+        "end": 142
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Confirms Dorothe Vaz Do received the pantry challenge",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Dorothe",
+        "start": 9,
+        "end": 16
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Vaz Do",
+        "start": 17,
+        "end": 23
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "That's so cool! I'm actually studying the evolution of Mrs art. Can you send me some pics of the Madame exhibition?",
+    "ground_truth": [
+      {
+        "tag": "TITLE",
+        "value": "Mrs",
+        "start": 55,
+        "end": 58
+      },
+      {
+        "tag": "TITLE",
+        "value": "Madame",
+        "start": 97,
+        "end": 103
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Please contact Miss Kessi Kouanda for assistance.",
+    "ground_truth": [
+      {
+        "tag": "TITLE",
+        "value": "Miss",
+        "start": 15,
+        "end": 19
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Kessi",
+        "start": 20,
+        "end": 25
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Kouanda",
+        "start": 26,
+        "end": 33
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Madona",
+        "start": 6,
+        "end": 12
+      },
+      {
+        "tag": "STREET",
+        "value": "Kathotiya Road",
+        "start": 81,
+        "end": 95
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "426",
+        "start": 96,
+        "end": 99
+      },
+      {
+        "tag": "CITY",
+        "value": "Khanapur Parwaliya Sadak",
+        "start": 101,
+        "end": 125
+      },
+      {
+        "tag": "DATE",
+        "value": "23/01/1993",
+        "start": 129,
+        "end": 139
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Jumana's Archery Equipment Inspection - 27/11/1941",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Jumana",
+        "start": 0,
+        "end": 6
+      },
+      {
+        "tag": "DATE",
+        "value": "27/11/1941",
+        "start": 40,
+        "end": 50
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Personal microclimate survey: What is your preferred air quality index, Simeon?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Simeon",
+        "start": 72,
+        "end": 78
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "19:27:28 Cheick: 'Sure, it is YZ7420622.'",
+    "ground_truth": [
+      {
+        "tag": "TIME",
+        "value": "19:27:28",
+        "start": 0,
+        "end": 8
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Cheick",
+        "start": 9,
+        "end": 15
+      },
+      {
+        "tag": "PASSPORTNUM",
+        "value": "YZ7420622",
+        "start": 30,
+        "end": 39
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Pasha Franklim: Hey Farha! My bonsai tree is dying, I need your help ASAP.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Pasha Franklim",
+        "start": 0,
+        "end": 14
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Farha",
+        "start": 20,
+        "end": 25
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "I want to surprise Golnar on their birthday. Can you guys keep a secret?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Golnar",
+        "start": 19,
+        "end": 25
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Eqrem",
+        "start": 101,
+        "end": 106
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "0128 62 277 6657",
+        "start": 110,
+        "end": 126
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Hello Luningning, this is Delegate Klenger from the aquarium maintenance team. We need your 4340766747589394 to process your payment.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Luningning",
+        "start": 6,
+        "end": 16
+      },
+      {
+        "tag": "TITLE",
+        "value": "Delegate",
+        "start": 26,
+        "end": 34
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Klenger",
+        "start": 35,
+        "end": 42
+      },
+      {
+        "tag": "CREDITCARDNUMBER",
+        "value": "4340766747589394",
+        "start": 92,
+        "end": 108
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "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",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Cornell Karthipan",
+        "start": 42,
+        "end": 59
+      },
+      {
+        "tag": "IDCARDNUM",
+        "value": "NP82IDQ3SK",
+        "start": 117,
+        "end": 127
+      },
+      {
+        "tag": "DATE",
+        "value": "13/12/1979",
+        "start": 140,
+        "end": 150
+      },
+      {
+        "tag": "TELEPHONENUM",
+        "value": "06.85-04-19 29",
+        "start": 168,
+        "end": 182
+      },
+      {
+        "tag": "STREET",
+        "value": "Meerut-Prayagraj Expressway",
+        "start": 196,
+        "end": 223
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "340",
+        "start": 224,
+        "end": 227
+      },
+      {
+        "tag": "CITY",
+        "value": "Mohanlal Ganj",
+        "start": 229,
+        "end": 242
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "509324",
+        "start": 244,
+        "end": 250
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "New task assigned to Samaher: Update the 1904 and V0B for the upcoming event.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Samaher",
+        "start": 21,
+        "end": 28
+      },
+      {
+        "tag": "BUILDINGNUM",
+        "value": "1904",
+        "start": 41,
+        "end": 45
+      },
+      {
+        "tag": "ZIPCODE",
+        "value": "V0B",
+        "start": 50,
+        "end": 53
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "How old is Loukian's child? We need to plan the folk dance moves accordingly.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Loukian",
+        "start": 11,
+        "end": 18
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "The following individuals have contributed to this project: Blenda Stoia, Elycia Kirchmayr Losmaz, and Gasser Ethanaël Dutranoy.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Blenda",
+        "start": 60,
+        "end": 66
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Stoia",
+        "start": 67,
+        "end": 72
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Elycia",
+        "start": 74,
+        "end": 80
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Kirchmayr Losmaz",
+        "start": 81,
+        "end": 97
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Gasser Ethanaël",
+        "start": 103,
+        "end": 118
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Dutranoy",
+        "start": 119,
+        "end": 127
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Enjoying the satirical poems of Jianchao Scrivano. Great perspectives.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Jianchao",
+        "start": 32,
+        "end": 40
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Scrivano",
+        "start": 41,
+        "end": 49
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "I've started learning copperplate script from Master Slatinská Endmann Tandon. Anyone know of good resources?",
+    "ground_truth": [
+      {
+        "tag": "TITLE",
+        "value": "Master",
+        "start": 46,
+        "end": 52
+      },
+      {
+        "tag": "SURNAME",
+        "value": "Slatinská Endmann Tandon",
+        "start": 53,
+        "end": 77
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "The conversation is about the educational journey of Giusva in linguistics and semiotics.",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Giusva",
+        "start": 53,
+        "end": 59
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Caylan François-Joseph: 'I have it, 1996NC@aol.com me and I'll send it over'",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Caylan François-Joseph",
+        "start": 0,
+        "end": 22
+      },
+      {
+        "tag": "EMAIL",
+        "value": "1996NC@aol.com",
+        "start": 36,
+        "end": 50
+      }
+    ],
+    "predictions": []
+  },
+  {
+    "source_text": "Grayson Albonit: Sounds like fun! What's the recipe? Does it include Manojl's secret ingredient?",
+    "ground_truth": [
+      {
+        "tag": "GIVENNAME",
+        "value": "Grayson Albonit",
+        "start": 0,
+        "end": 15
+      },
+      {
+        "tag": "GIVENNAME",
+        "value": "Manojl",
+        "start": 69,
+        "end": 75
+      }
+    ],
+    "predictions": []
+  }
+]

ai4privacy/SpanBased-CustomDeBERTa/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a460a9fbab227d4208ae273ff30b48be219b139ac48162ebb79f9abf90dd1f72
+size 741414031

ai4privacy/SpanBased-CustomDeBERTa/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}