lightweight-hybrid-v1

Worst Test Samples

Weak Labels Not Found In CV Text

Raw Metrics

{
  "token_entity_precision": 0.3507,
  "token_entity_recall": 0.5903,
  "token_entity_f1": 0.44,
  "span_precision": 0.1492,
  "span_recall": 0.4731,
  "span_f1": 0.2268,
  "gold_span_count": 334,
  "predicted_span_count": 1059,
  "field_metrics": [
    {
      "field": "contact",
      "precision": 0.4712,
      "recall": 0.7313,
      "f1": 0.5731,
      "tp": 49,
      "fp": 55,
      "fn": 18
    },
    {
      "field": "location",
      "precision": 0.3778,
      "recall": 0.3148,
      "f1": 0.3434,
      "tp": 17,
      "fp": 28,
      "fn": 37
    },
    {
      "field": "skills",
      "precision": 0.3283,
      "recall": 0.7228,
      "f1": 0.4515,
      "tp": 219,
      "fp": 448,
      "fn": 84
    },
    {
      "field": "education",
      "precision": 0.5123,
      "recall": 0.6561,
      "f1": 0.5754,
      "tp": 166,
      "fp": 158,
      "fn": 87
    },
    {
      "field": "employment",
      "precision": 0.4389,
      "recall": 0.7381,
      "f1": 0.5505,
      "tp": 248,
      "fp": 317,
      "fn": 88
    }
  ],
  "worst_samples": [
    {
      "sample_id": 26,
      "file_name": "CV_Lajmi_2022.docx",
      "label_source": "corrected",
      "gold_span_count": 47,
      "predicted_span_count": 127,
      "false_positive_count": 122,
      "false_negative_count": 42,
      "token_error_count": 205,
      "span_precision": 0.0394,
      "span_recall": 0.1064,
      "span_f1": 0.0575,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "CIVIL",
          "start_token": 56,
          "end_token": 57
        },
        {
          "label": "CERTIFICATION",
          "text": "AUTHORITY",
          "start_token": 58,
          "end_token": 59
        },
        {
          "label": "CERTIFICATION",
          "text": "(",
          "start_token": 73,
          "end_token": 74
        },
        {
          "label": "CERTIFICATION",
          "text": "BY",
          "start_token": 75,
          "end_token": 76
        },
        {
          "label": "CERTIFICATION",
          "text": "Safety",
          "start_token": 144,
          "end_token": 145
        },
        {
          "label": "CERTIFICATION",
          "text": "Safety",
          "start_token": 148,
          "end_token": 149
        },
        {
          "label": "CERTIFICATION",
          "text": ") Safety",
          "start_token": 271,
          "end_token": 273
        },
        {
          "label": "CERTIFICATION",
          "text": "training for ATC",
          "start_token": 485,
          "end_token": 488
        },
        {
          "label": "CERTIFICATION",
          "text": "2012",
          "start_token": 575,
          "end_token": 576
        },
        {
          "label": "CERTIFICATION",
          "text": "2015 FRENCH",
          "start_token": 589,
          "end_token": 591
        },
        {
          "label": "CERTIFICATION",
          "text": "training",
          "start_token": 618,
          "end_token": 619
        },
        {
          "label": "CERTIFICATION",
          "text": "certification Audit Safety Management System",
          "start_token": 620,
          "end_token": 625
        }
      ],
      "false_negatives": [
        {
          "label": "CERTIFICATION",
          "text": "aerodrome certification audit",
          "start_token": 102,
          "end_token": 105
        },
        {
          "label": "CERTIFICATION",
          "text": "Human factor training",
          "start_token": 616,
          "end_token": 619
        },
        {
          "label": "CERTIFICATION",
          "text": "Safety Management System Module 1",
          "start_token": 622,
          "end_token": 627
        },
        {
          "label": "CERTIFICATION",
          "text": "Occurence report system",
          "start_token": 627,
          "end_token": 630
        },
        {
          "label": "CERTIFICATION",
          "text": "Risk assessment and Safety study",
          "start_token": 630,
          "end_token": 635
        },
        {
          "label": "CERTIFICATION",
          "text": "Advanced Safety Study",
          "start_token": 640,
          "end_token": 643
        },
        {
          "label": "CERTIFICATION",
          "text": "Basic Security training",
          "start_token": 646,
          "end_token": 649
        },
        {
          "label": "CERTIFICATION",
          "text": "GNS1 : Safety Managment System",
          "start_token": 649,
          "end_token": 654
        },
        {
          "label": "CERTIFICATION",
          "text": "Security of cargo and mail",
          "start_token": 654,
          "end_token": 659
        },
        {
          "label": "CERTIFICATION",
          "text": "GSN 3- Emergency Planning and crisis management",
          "start_token": 659,
          "end_token": 666
        },
        {
          "label": "CERTIFICATION",
          "text": "GSN 2 - Airside Safety & Operations",
          "start_token": 668,
          "end_token": 675
        },
        {
          "label": "CERTIFICATION",
          "text": "Airport Environmental Management",
          "start_token": 680,
          "end_token": 683
        }
      ]
    },
    {
      "sample_id": 6,
      "file_name": "A_K_Dwivedi_336829.pdf",
      "label_source": "corrected",
      "gold_span_count": 29,
      "predicted_span_count": 216,
      "false_positive_count": 208,
      "false_negative_count": 21,
      "token_error_count": 271,
      "span_precision": 0.037,
      "span_recall": 0.2759,
      "span_f1": 0.0653,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "CC8800-2200",
          "start_token": 171,
          "end_token": 172
        },
        {
          "label": "CERTIFICATION",
          "text": "Safety",
          "start_token": 334,
          "end_token": 335
        },
        {
          "label": "CERTIFICATION",
          "text": "Health",
          "start_token": 336,
          "end_token": 337
        },
        {
          "label": "CERTIFICATION",
          "text": "Productivity",
          "start_token": 433,
          "end_token": 434
        },
        {
          "label": "CERTIFICATION",
          "text": "Safety",
          "start_token": 440,
          "end_token": 441
        },
        {
          "label": "CERTIFICATION",
          "text": ")",
          "start_token": 1003,
          "end_token": 1004
        },
        {
          "label": "CERTIFICATION",
          "text": "Organization",
          "start_token": 1176,
          "end_token": 1177
        },
        {
          "label": "CERTIFICATION",
          "text": "Training",
          "start_token": 1437,
          "end_token": 1438
        },
        {
          "label": "CERTIFICATION",
          "text": "(",
          "start_token": 1464,
          "end_token": 1465
        },
        {
          "label": "CERTIFICATION",
          "text": ")",
          "start_token": 1466,
          "end_token": 1467
        },
        {
          "label": "CERTIFICATION",
          "text": "Dealer",
          "start_token": 1525,
          "end_token": 1526
        },
        {
          "label": "CERTIFICATION",
          "text": "/",
          "start_token": 1713,
          "end_token": 1714
        }
      ],
      "false_negatives": [
        {
          "label": "COUNTRY",
          "text": "Kuwait",
          "start_token": 25,
          "end_token": 26
        },
        {
          "label": "EDU_DEGREE",
          "text": "A.M.I.E. B.E. Mechanical Engineering",
          "start_token": 312,
          "end_token": 316
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "I.E.R.T. Allahabad",
          "start_token": 306,
          "end_token": 308
        },
        {
          "label": "EXP_COMPANY",
          "text": "M/s. BURGAN DRILLING COMPANY",
          "start_token": 13,
          "end_token": 17
        },
        {
          "label": "EXP_COMPANY",
          "text": "M/S JASSIM TRANSPORT & STEVEDORING Co. WLL",
          "start_token": 897,
          "end_token": 904
        },
        {
          "label": "EXP_COMPANY",
          "text": "M/S AL-IRSHAD GEN. TRADING & CONT. COMPANY",
          "start_token": 1045,
          "end_token": 1052
        },
        {
          "label": "EXP_COMPANY",
          "text": "M/S SHAHEEN AL- GHANIM , ROAD AND BRIDGE CONST. Co.",
          "start_token": 1128,
          "end_token": 1138
        },
        {
          "label": "EXP_COMPANY",
          "text": "M/S GAJRA BEVEL GRARS LTD.",
          "start_token": 1458,
          "end_token": 1463
        },
        {
          "label": "EXP_COMPANY",
          "text": "M/S WEAVER TRACKS PVT LTD",
          "start_token": 1557,
          "end_token": 1562
        },
        {
          "label": "EXP_COMPANY",
          "text": "M/S TATA ENGINEERING & LOCOMOTIVE CO. LTD",
          "start_token": 1698,
          "end_token": 1705
        },
        {
          "label": "EXP_POSITION",
          "text": "WORKSHOP MANAGER",
          "start_token": 6,
          "end_token": 8
        },
        {
          "label": "EXP_POSITION",
          "text": "Fleet Maintenance Manager",
          "start_token": 665,
          "end_token": 668
        }
      ]
    },
    {
      "sample_id": 20,
      "file_name": "344_MUHAMMAD_JC-40_1.pdf",
      "label_source": "ai",
      "gold_span_count": 13,
      "predicted_span_count": 51,
      "false_positive_count": 48,
      "false_negative_count": 10,
      "token_error_count": 93,
      "span_precision": 0.0588,
      "span_recall": 0.2308,
      "span_f1": 0.0938,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "(",
          "start_token": 189,
          "end_token": 190
        },
        {
          "label": "CERTIFICATION",
          "text": "Basic",
          "start_token": 408,
          "end_token": 409
        },
        {
          "label": "CERTIFICATION",
          "text": "5000 60000",
          "start_token": 419,
          "end_token": 421
        },
        {
          "label": "CERTIFICATION",
          "text": ")",
          "start_token": 428,
          "end_token": 429
        },
        {
          "label": "CERTIFICATION",
          "text": "3000 36000",
          "start_token": 433,
          "end_token": 435
        },
        {
          "label": "CERTIFICATION",
          "text": ")",
          "start_token": 442,
          "end_token": 443
        },
        {
          "label": "EDU_DEGREE",
          "text": "Degree",
          "start_token": 157,
          "end_token": 158
        },
        {
          "label": "EDU_DEGREE",
          "text": "Specialization",
          "start_token": 159,
          "end_token": 160
        },
        {
          "label": "EDU_DEGREE",
          "text": "Technology",
          "start_token": 170,
          "end_token": 171
        },
        {
          "label": "EDU_DEGREE",
          "text": "Master of Science in Electrical Engineering",
          "start_token": 175,
          "end_token": 181
        },
        {
          "label": "EDU_DEGREE",
          "text": "specified",
          "start_token": 182,
          "end_token": 183
        },
        {
          "label": "EDU_DEGREE",
          "text": "Science )",
          "start_token": 190,
          "end_token": 192
        }
      ],
      "false_negatives": [
        {
          "label": "EDU_DEGREE",
          "text": "Education type : Bachelors",
          "start_token": 266,
          "end_token": 270
        },
        {
          "label": "EDU_DEGREE",
          "text": "Education : Degree",
          "start_token": 346,
          "end_token": 349
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Education : Degree",
          "start_token": 155,
          "end_token": 158
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Specialization : Information Technology , Electrical , Electrical ,",
          "start_token": 199,
          "end_token": 208
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Job :",
          "start_token": 226,
          "end_token": 228
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Offer :",
          "start_token": 371,
          "end_token": 373
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Country : Algeria",
          "start_token": 449,
          "end_token": 452
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "What is the meaning of below tags",
          "start_token": 458,
          "end_token": 465
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "System :",
          "start_token": 502,
          "end_token": 504
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Email signature :",
          "start_token": 514,
          "end_token": 517
        }
      ]
    },
    {
      "sample_id": 34,
      "file_name": "Resume_Maheshkumar_CACPA_Bcom.pdf",
      "label_source": "corrected",
      "gold_span_count": 38,
      "predicted_span_count": 117,
      "false_positive_count": 109,
      "false_negative_count": 30,
      "token_error_count": 157,
      "span_precision": 0.0684,
      "span_recall": 0.2105,
      "span_f1": 0.1032,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "2015 Certified Public",
          "start_token": 15,
          "end_token": 18
        },
        {
          "label": "CERTIFICATION",
          "text": "( CPA )",
          "start_token": 19,
          "end_token": 22
        },
        {
          "label": "CERTIFICATION",
          "text": "(",
          "start_token": 42,
          "end_token": 43
        },
        {
          "label": "CERTIFICATION",
          "text": ")",
          "start_token": 44,
          "end_token": 45
        },
        {
          "label": "CERTIFICATION",
          "text": "(",
          "start_token": 128,
          "end_token": 129
        },
        {
          "label": "CERTIFICATION",
          "text": "( CAD",
          "start_token": 135,
          "end_token": 137
        },
        {
          "label": "CERTIFICATION",
          "text": "1",
          "start_token": 408,
          "end_token": 409
        },
        {
          "label": "CERTIFICATION",
          "text": "Institute",
          "start_token": 420,
          "end_token": 421
        },
        {
          "label": "CERTIFICATION",
          "text": "ICAI",
          "start_token": 427,
          "end_token": 428
        },
        {
          "label": "CERTIFICATION",
          "text": "systems",
          "start_token": 639,
          "end_token": 640
        },
        {
          "label": "CERTIFICATION",
          "text": "Focus ( ERP )",
          "start_token": 788,
          "end_token": 792
        },
        {
          "label": "CERTIFICATION",
          "text": "Dynamics",
          "start_token": 793,
          "end_token": 794
        }
      ],
      "false_negatives": [
        {
          "label": "CERTIFICATION",
          "text": "Certified Public Accountant ( CPA )",
          "start_token": 16,
          "end_token": 22
        },
        {
          "label": "EDU_DEGREE",
          "text": "Chartered Accountancy",
          "start_token": 26,
          "end_token": 28
        },
        {
          "label": "EDU_DEGREE",
          "text": "Company Secretary executive",
          "start_token": 449,
          "end_token": 452
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "CPA Australia , Australia",
          "start_token": 22,
          "end_token": 26
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Institute of Chartered Accountants of India ( ICAI ) , India",
          "start_token": 28,
          "end_token": 39
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Institute of Company Secretaries of India ( ICSI )",
          "start_token": 454,
          "end_token": 463
        },
        {
          "label": "EXP_COMPANY",
          "text": "Magna Tyres Group , UAE",
          "start_token": 66,
          "end_token": 71
        },
        {
          "label": "EXP_COMPANY",
          "text": "Mills Trading LLC , UAE",
          "start_token": 187,
          "end_token": 192
        },
        {
          "label": "EXP_COMPANY",
          "text": "Agro Indus Credits Limited , India",
          "start_token": 319,
          "end_token": 325
        },
        {
          "label": "EXP_COMPANY",
          "text": "G Joseph & Associates , Chartered Accountants , India",
          "start_token": 591,
          "end_token": 600
        },
        {
          "label": "EXP_POSITION",
          "text": "Finance Manager",
          "start_token": 64,
          "end_token": 66
        },
        {
          "label": "EXP_POSITION",
          "text": "Finance Manager",
          "start_token": 185,
          "end_token": 187
        }
      ]
    },
    {
      "sample_id": 23,
      "file_name": "Arsh_CV_V2.pdf",
      "label_source": "corrected",
      "gold_span_count": 39,
      "predicted_span_count": 144,
      "false_positive_count": 130,
      "false_negative_count": 25,
      "token_error_count": 151,
      "span_precision": 0.0972,
      "span_recall": 0.359,
      "span_f1": 0.153,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "& Developing",
          "start_token": 62,
          "end_token": 64
        },
        {
          "label": "CERTIFICATION",
          "text": "2015",
          "start_token": 112,
          "end_token": 113
        },
        {
          "label": "CERTIFICATION",
          "text": "2015",
          "start_token": 128,
          "end_token": 129
        },
        {
          "label": "CERTIFICATION",
          "text": "Digital",
          "start_token": 190,
          "end_token": 191
        },
        {
          "label": "CERTIFICATION",
          "text": "2014",
          "start_token": 207,
          "end_token": 208
        },
        {
          "label": "CERTIFICATION",
          "text": "Interest",
          "start_token": 266,
          "end_token": 267
        },
        {
          "label": "CERTIFICATION",
          "text": "Language",
          "start_token": 300,
          "end_token": 301
        },
        {
          "label": "CERTIFICATION",
          "text": "Training",
          "start_token": 306,
          "end_token": 307
        },
        {
          "label": "CITY",
          "text": "Dubai",
          "start_token": 110,
          "end_token": 111
        },
        {
          "label": "EDU_DEGREE",
          "text": "in",
          "start_token": 19,
          "end_token": 20
        },
        {
          "label": "EDU_DEGREE",
          "text": "Marketing",
          "start_token": 32,
          "end_token": 33
        },
        {
          "label": "EDU_DEGREE",
          "text": "Technologies",
          "start_token": 70,
          "end_token": 71
        }
      ],
      "false_negatives": [
        {
          "label": "CITY",
          "text": "Dubai",
          "start_token": 204,
          "end_token": 205
        },
        {
          "label": "COUNTRY",
          "text": "UAE",
          "start_token": 206,
          "end_token": 207
        },
        {
          "label": "EDU_DEGREE",
          "text": "Computer Science Engineering",
          "start_token": 123,
          "end_token": 126
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Indian Institute of Technology , Bombay , India",
          "start_token": 115,
          "end_token": 123
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Canadian University of Dubai , Dubai , UAE",
          "start_token": 129,
          "end_token": 137
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Board of Higher Secondary Education , Hyderabad , India",
          "start_token": 145,
          "end_token": 154
        },
        {
          "label": "EXP_COMPANY",
          "text": "Grand Optics LLC",
          "start_token": 201,
          "end_token": 204
        },
        {
          "label": "EXP_COMPANY",
          "text": "Al Khatib Properties LLC",
          "start_token": 212,
          "end_token": 216
        },
        {
          "label": "EXP_COMPANY",
          "text": "Marine Registration Services LLC",
          "start_token": 224,
          "end_token": 228
        },
        {
          "label": "EXP_POSITION",
          "text": "IT Director",
          "start_token": 12,
          "end_token": 14
        },
        {
          "label": "EXP_POSITION",
          "text": "Project Manager",
          "start_token": 199,
          "end_token": 201
        },
        {
          "label": "LOCATION",
          "text": "Port Saeed",
          "start_token": 105,
          "end_token": 107
        }
      ]
    },
    {
      "sample_id": 8,
      "file_name": "Rakshani-CV.docx",
      "label_source": "corrected",
      "gold_span_count": 29,
      "predicted_span_count": 37,
      "false_positive_count": 28,
      "false_negative_count": 20,
      "token_error_count": 52,
      "span_precision": 0.2432,
      "span_recall": 0.3103,
      "span_f1": 0.2727,
      "false_positives": [
        {
          "label": "EDU_DEGREE",
          "text": "higher secondary from",
          "start_token": 87,
          "end_token": 90
        },
        {
          "label": "EDU_DEGREE",
          "text": "Secondary School from",
          "start_token": 94,
          "end_token": 97
        },
        {
          "label": "EDU_DEGREE",
          "text": "–",
          "start_token": 114,
          "end_token": 115
        },
        {
          "label": "EDU_DEGREE",
          "text": "Consultancy –",
          "start_token": 203,
          "end_token": 205
        },
        {
          "label": "EDU_DEGREE",
          "text": "LANGUAGES",
          "start_token": 282,
          "end_token": 283
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Mumbai",
          "start_token": 41,
          "end_token": 42
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Gadge",
          "start_token": 81,
          "end_token": 82
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Baba University",
          "start_token": 82,
          "end_token": 84
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Bhagyashree College March",
          "start_token": 90,
          "end_token": 93
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Cross",
          "start_token": 98,
          "end_token": 99
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "High School , Amravati.",
          "start_token": 99,
          "end_token": 103
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Mumbai",
          "start_token": 149,
          "end_token": 150
        }
      ],
      "false_negatives": [
        {
          "label": "COUNTRY",
          "text": "Indian",
          "start_token": 18,
          "end_token": 19
        },
        {
          "label": "EDU_DEGREE",
          "text": "Pursuing graduation",
          "start_token": 77,
          "end_token": 79
        },
        {
          "label": "EDU_DEGREE",
          "text": "higher secondary",
          "start_token": 87,
          "end_token": 89
        },
        {
          "label": "EDU_DEGREE",
          "text": "Secondary School",
          "start_token": 94,
          "end_token": 96
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Sant Gadge Baba University",
          "start_token": 80,
          "end_token": 84
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Bhagyashree College",
          "start_token": 90,
          "end_token": 92
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Holy Cross High School , Amravati.",
          "start_token": 97,
          "end_token": 103
        },
        {
          "label": "EXP_COMPANY",
          "text": "Ashoka Hotel – Nagpur",
          "start_token": 108,
          "end_token": 112
        },
        {
          "label": "EXP_COMPANY",
          "text": "Vastusankalp Group – Mumbai",
          "start_token": 146,
          "end_token": 150
        },
        {
          "label": "EXP_COMPANY",
          "text": "Morpheus Consultancy – Mumbai",
          "start_token": 202,
          "end_token": 206
        },
        {
          "label": "EXP_POSITION",
          "text": "Property Consultant",
          "start_token": 159,
          "end_token": 161
        },
        {
          "label": "EXP_POSITION",
          "text": "HR Consultant/Recruiter",
          "start_token": 215,
          "end_token": 217
        }
      ]
    },
    {
      "sample_id": 32,
      "file_name": "JESSA_BUNAGAN_NEWW.pdf",
      "label_source": "corrected",
      "gold_span_count": 30,
      "predicted_span_count": 53,
      "false_positive_count": 41,
      "false_negative_count": 18,
      "token_error_count": 48,
      "span_precision": 0.2264,
      "span_recall": 0.4,
      "span_f1": 0.2892,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "Office",
          "start_token": 34,
          "end_token": 35
        },
        {
          "label": "CERTIFICATION",
          "text": "Language",
          "start_token": 89,
          "end_token": 90
        },
        {
          "label": "CERTIFICATION",
          "text": "Foundation",
          "start_token": 197,
          "end_token": 198
        },
        {
          "label": "CERTIFICATION",
          "text": "Diploma",
          "start_token": 395,
          "end_token": 396
        },
        {
          "label": "EDU_DEGREE",
          "text": "Tagalog",
          "start_token": 91,
          "end_token": 92
        },
        {
          "label": "EDU_DEGREE",
          "text": "Microfinance",
          "start_token": 192,
          "end_token": 193
        },
        {
          "label": "EDU_DEGREE",
          "text": "–",
          "start_token": 201,
          "end_token": 202
        },
        {
          "label": "EDU_DEGREE",
          "text": "Cashier",
          "start_token": 307,
          "end_token": 308
        },
        {
          "label": "EDU_DEGREE",
          "text": "–",
          "start_token": 317,
          "end_token": 318
        },
        {
          "label": "EDU_DEGREE",
          "text": "High",
          "start_token": 381,
          "end_token": 382
        },
        {
          "label": "EDU_DEGREE",
          "text": "Diploma",
          "start_token": 383,
          "end_token": 384
        },
        {
          "label": "EDU_DEGREE",
          "text": "Elementary",
          "start_token": 394,
          "end_token": 395
        }
      ],
      "false_negatives": [
        {
          "label": "EDU_DEGREE",
          "text": "High School Diploma",
          "start_token": 381,
          "end_token": 384
        },
        {
          "label": "EDU_DEGREE",
          "text": "Elementary Diploma",
          "start_token": 394,
          "end_token": 396
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Cagayan State University",
          "start_token": 378,
          "end_token": 381
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Enrile East Central School Magalalag",
          "start_token": 401,
          "end_token": 406
        },
        {
          "label": "EXP_COMPANY",
          "text": "Saudia Hypermarket Qatar",
          "start_token": 141,
          "end_token": 144
        },
        {
          "label": "EXP_COMPANY",
          "text": "Asa Philippines Foundation Inc.",
          "start_token": 195,
          "end_token": 199
        },
        {
          "label": "EXP_COMPANY",
          "text": "ACTIVE COOPERATION FOR ECONOMIC SUSTENANCE MULTI-PURPOSE COOPERATIVE",
          "start_token": 249,
          "end_token": 256
        },
        {
          "label": "EXP_COMPANY",
          "text": "SM HYPER MARKET CHERRY CONGRESIONAL",
          "start_token": 310,
          "end_token": 315
        },
        {
          "label": "EXP_POSITION",
          "text": "Microfinance Officer",
          "start_token": 192,
          "end_token": 194
        },
        {
          "label": "EXP_POSITION",
          "text": "Cashier",
          "start_token": 262,
          "end_token": 263
        },
        {
          "label": "LANGUAGE",
          "text": "Tagalog",
          "start_token": 91,
          "end_token": 92
        },
        {
          "label": "LOCATION",
          "text": "#Street 59 house #156",
          "start_token": 19,
          "end_token": 23
        }
      ]
    },
    {
      "sample_id": 50,
      "file_name": "Ahmed_Awad.docx",
      "label_source": "corrected",
      "gold_span_count": 34,
      "predicted_span_count": 138,
      "false_positive_count": 109,
      "false_negative_count": 5,
      "token_error_count": 205,
      "span_precision": 0.2101,
      "span_recall": 0.8529,
      "span_f1": 0.3372,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "(",
          "start_token": 11,
          "end_token": 12
        },
        {
          "label": "CERTIFICATION",
          "text": "Quality",
          "start_token": 47,
          "end_token": 48
        },
        {
          "label": "CERTIFICATION",
          "text": "System",
          "start_token": 49,
          "end_token": 50
        },
        {
          "label": "CERTIFICATION",
          "text": ",",
          "start_token": 117,
          "end_token": 118
        },
        {
          "label": "CERTIFICATION",
          "text": "Management System ( QMS",
          "start_token": 265,
          "end_token": 269
        },
        {
          "label": "CERTIFICATION",
          "text": "Quality Management System Auditor/Lead Auditor certified by the IRCA",
          "start_token": 326,
          "end_token": 335
        },
        {
          "label": "CERTIFICATION",
          "text": "9000",
          "start_token": 338,
          "end_token": 339
        },
        {
          "label": "CERTIFICATION",
          "text": "9001",
          "start_token": 343,
          "end_token": 344
        },
        {
          "label": "CERTIFICATION",
          "text": "Institute of Leadership and Management Endorsed Award certified by ILM.",
          "start_token": 359,
          "end_token": 369
        },
        {
          "label": "CERTIFICATION",
          "text": "Internal Auditor ( OHSAS 18001 Series Standards )",
          "start_token": 412,
          "end_token": 420
        },
        {
          "label": "CERTIFICATION",
          "text": "ISO 9000 : 2000 FOUNDATION",
          "start_token": 421,
          "end_token": 426
        },
        {
          "label": "CERTIFICATION",
          "text": "ISO 14000 & EMAS FOUNDATION.",
          "start_token": 427,
          "end_token": 432
        }
      ],
      "false_negatives": [
        {
          "label": "EDU_DEGREE",
          "text": "A2 Level",
          "start_token": 1836,
          "end_token": 1838
        },
        {
          "label": "EDU_UNIVERSITY",
          "text": "Shorefields Comprehensive School",
          "start_token": 1848,
          "end_token": 1851
        },
        {
          "label": "EXP_COMPANY",
          "text": "STRATA",
          "start_token": 56,
          "end_token": 57
        },
        {
          "label": "LOCATION",
          "text": "Al Manara Tower",
          "start_token": 5,
          "end_token": 8
        },
        {
          "label": "SKILL",
          "text": "Communication",
          "start_token": 631,
          "end_token": 632
        }
      ]
    },
    {
      "sample_id": 35,
      "file_name": "Sarang_O_original_-_Copy.pdf",
      "label_source": "ai",
      "gold_span_count": 35,
      "predicted_span_count": 80,
      "false_positive_count": 49,
      "false_negative_count": 4,
      "token_error_count": 57,
      "span_precision": 0.3875,
      "span_recall": 0.8857,
      "span_f1": 0.5391,
      "false_positives": [
        {
          "label": "EDU_DEGREE",
          "text": "Engineering",
          "start_token": 235,
          "end_token": 236
        },
        {
          "label": "EXP_COMPANY",
          "text": "Design",
          "start_token": 266,
          "end_token": 267
        },
        {
          "label": "EXP_COMPANY",
          "text": ")",
          "start_token": 273,
          "end_token": 274
        },
        {
          "label": "EXP_COMPANY",
          "text": "&",
          "start_token": 500,
          "end_token": 501
        },
        {
          "label": "EXP_COMPANY",
          "text": "&",
          "start_token": 524,
          "end_token": 525
        },
        {
          "label": "EXP_POSITION",
          "text": "Sales",
          "start_token": 438,
          "end_token": 439
        },
        {
          "label": "EXP_POSITION",
          "text": "&",
          "start_token": 505,
          "end_token": 506
        },
        {
          "label": "LOCATION",
          "text": "Duabi",
          "start_token": 6,
          "end_token": 7
        },
        {
          "label": "NAME",
          "text": "",
          "start_token": 0,
          "end_token": 1
        },
        {
          "label": "PROFESSION",
          "text": "&",
          "start_token": 239,
          "end_token": 240
        },
        {
          "label": "PROFESSION",
          "text": "&",
          "start_token": 483,
          "end_token": 484
        },
        {
          "label": "SKILL",
          "text": "and",
          "start_token": 80,
          "end_token": 81
        }
      ],
      "false_negatives": [
        {
          "label": "SKILL",
          "text": "Incoterms",
          "start_token": 507,
          "end_token": 508
        },
        {
          "label": "SKILL",
          "text": "Contractual Knowledge",
          "start_token": 509,
          "end_token": 511
        },
        {
          "label": "SKILL",
          "text": "Team leader",
          "start_token": 511,
          "end_token": 513
        },
        {
          "label": "SKILL",
          "text": "CRM",
          "start_token": 526,
          "end_token": 527
        }
      ]
    },
    {
      "sample_id": 13,
      "file_name": "Khyati_Mayur_Trivedi_-_CV.docx",
      "label_source": "corrected",
      "gold_span_count": 40,
      "predicted_span_count": 96,
      "false_positive_count": 57,
      "false_negative_count": 1,
      "token_error_count": 82,
      "span_precision": 0.4062,
      "span_recall": 0.975,
      "span_f1": 0.5735,
      "false_positives": [
        {
          "label": "CERTIFICATION",
          "text": "Training",
          "start_token": 633,
          "end_token": 634
        },
        {
          "label": "CERTIFICATION",
          "text": "Training",
          "start_token": 1211,
          "end_token": 1212
        },
        {
          "label": "CERTIFICATION",
          "text": "Training",
          "start_token": 1385,
          "end_token": 1386
        },
        {
          "label": "COUNTRY",
          "text": "United",
          "start_token": 737,
          "end_token": 738
        },
        {
          "label": "EDU_DEGREE",
          "text": "in",
          "start_token": 990,
          "end_token": 991
        },
        {
          "label": "EDU_DEGREE",
          "text": "2010",
          "start_token": 1487,
          "end_token": 1488
        },
        {
          "label": "EXP_COMPANY",
          "text": ",",
          "start_token": 14,
          "end_token": 15
        },
        {
          "label": "EXP_COMPANY",
          "text": "P",
          "start_token": 248,
          "end_token": 249
        },
        {
          "label": "EXP_COMPANY",
          "text": "F.GHEEWALA- ZTECH MANPOWER SERVICES ,",
          "start_token": 355,
          "end_token": 360
        },
        {
          "label": "EXP_COMPANY",
          "text": "Services",
          "start_token": 595,
          "end_token": 596
        },
        {
          "label": "EXP_COMPANY",
          "text": "VAIBHAV LOAN SOLUTIONS & SERVICES – XX , India",
          "start_token": 642,
          "end_token": 651
        },
        {
          "label": "EXP_COMPANY",
          "text": "IT",
          "start_token": 731,
          "end_token": 732
        }
      ],
      "false_negatives": [
        {
          "label": "PHONE",
          "text": "( +971 ) 565 320 905",
          "start_token": 6,
          "end_token": 12
        }
      ]
    }
  ],
  "unmatched_label_count": 127,
  "unmatched_sample_count": 46,
  "unmatched_by_label": {
    "EXP_POSITION": 22,
    "COUNTRY": 17,
    "EDU_DEGREE": 16,
    "SKILL": 15,
    "CITY": 14,
    "EXP_COMPANY": 12,
    "CERTIFICATION": 10,
    "EDU_UNIVERSITY": 7,
    "PHONE": 6,
    "LINKEDIN": 3,
    "NAME": 2,
    "PROFESSION": 2,
    "LOCATION": 1
  },
  "per_label": {
    "B-CERTIFICATION": {
      "precision": 0.3103,
      "recall": 0.36,
      "f1": 0.3333,
      "support": 25.0
    },
    "B-CITY": {
      "precision": 0.5,
      "recall": 0.3333,
      "f1": 0.4,
      "support": 3.0
    },
    "B-COUNTRY": {
      "precision": 0.4,
      "recall": 0.4,
      "f1": 0.4,
      "support": 5.0
    },
    "B-EDU_DEGREE": {
      "precision": 0.5,
      "recall": 0.5263,
      "f1": 0.5128,
      "support": 19.0
    },
    "B-EDU_UNIVERSITY": {
      "precision": 0.5128,
      "recall": 0.5128,
      "f1": 0.5128,
      "support": 39.0
    },
    "B-EMAIL": {
      "precision": 0.7,
      "recall": 1.0,
      "f1": 0.8235,
      "support": 7.0
    },
    "B-EXP_COMPANY": {
      "precision": 0.3833,
      "recall": 0.575,
      "f1": 0.46,
      "support": 40.0
    },
    "B-EXP_POSITION": {
      "precision": 0.377,
      "recall": 0.5349,
      "f1": 0.4423,
      "support": 43.0
    },
    "B-LANGUAGE": {
      "precision": 0.6341,
      "recall": 0.9286,
      "f1": 0.7536,
      "support": 28.0
    },
    "B-LINKEDIN": {
      "precision": 1.0,
      "recall": 1.0,
      "f1": 1.0,
      "support": 1.0
    },
    "B-LOCATION": {
      "precision": 0.1875,
      "recall": 0.3,
      "f1": 0.2308,
      "support": 20.0
    },
    "B-NAME": {
      "precision": 0.3333,
      "recall": 0.5,
      "f1": 0.4,
      "support": 8.0
    },
    "B-PHONE": {
      "precision": 0.4118,
      "recall": 0.4667,
      "f1": 0.4375,
      "support": 15.0
    },
    "B-PROFESSION": {
      "precision": 0.1429,
      "recall": 0.1667,
      "f1": 0.1538,
      "support": 6.0
    },
    "B-SKILL": {
      "precision": 0.2468,
      "recall": 0.7838,
      "f1": 0.3754,
      "support": 74.0
    },
    "B-WEBSITE": {
      "precision": 0.0,
      "recall": 0.0,
      "f1": 0.0,
      "support": 1.0
    },
    "I-CERTIFICATION": {
      "precision": 0.3535,
      "recall": 0.6542,
      "f1": 0.459,
      "support": 107.0
    },
    "I-CITY": {
      "precision": 0.0,
      "recall": 0.0,
      "f1": 0.0,
      "support": 0.0
    },
    "I-COUNTRY": {
      "precision": 0.0,
      "recall": 0.0,
      "f1": 0.0,
      "support": 0.0
    },
    "I-EDU_DEGREE": {
      "precision": 0.2639,
      "recall": 0.8085,
      "f1": 0.3979,
      "support": 47.0
    },
    "I-EDU_UNIVERSITY": {
      "precision": 0.6364,
      "recall": 0.5203,
      "f1": 0.5725,
      "support": 148.0
    },
    "I-EXP_COMPANY": {
      "precision": 0.3321,
      "recall": 0.5973,
      "f1": 0.4269,
      "support": 149.0
    },
    "I-EXP_POSITION": {
      "precision": 0.4632,
      "recall": 0.7241,
      "f1": 0.565,
      "support": 87.0
    },
    "I-LANGUAGE": {
      "precision": 0.0,
      "recall": 0.0,
      "f1": 0.0,
      "support": 0.0
    },
    "I-LINKEDIN": {
      "precision": 1.0,
      "recall": 1.0,
      "f1": 1.0,
      "support": 2.0
    },
    "I-LOCATION": {
      "precision": 0.3333,
      "recall": 0.0769,
      "f1": 0.125,
      "support": 26.0
    },
    "I-NAME": {
      "precision": 0.24,
      "recall": 0.5,
      "f1": 0.3243,
      "support": 12.0
    },
    "I-PHONE": {
      "precision": 0.4595,
      "recall": 0.8095,
      "f1": 0.5862,
      "support": 21.0
    },
    "I-PROFESSION": {
      "precision": 0.0606,
      "recall": 0.1818,
      "f1": 0.0909,
      "support": 11.0
    },
    "I-SKILL": {
      "precision": 0.2152,
      "recall": 0.4928,
      "f1": 0.2996,
      "support": 69.0
    },
    "I-WEBSITE": {
      "precision": 0.0,
      "recall": 0.0,
      "f1": 0.0,
      "support": 0.0
    },
    "micro avg": {
      "precision": 0.3507,
      "recall": 0.5903,
      "f1": 0.44,
      "support": 1013.0
    }
  },
  "label_source_counts": {
    "corrected": 42,
    "ai": 6
  },
  "token_count": 51105,
  "train_token_count": 41901,
  "test_token_count": 9204,
  "entity_labels": [
    "B-CERTIFICATION",
    "B-CITY",
    "B-COUNTRY",
    "B-EDU_DEGREE",
    "B-EDU_UNIVERSITY",
    "B-EMAIL",
    "B-EXP_COMPANY",
    "B-EXP_POSITION",
    "B-LANGUAGE",
    "B-LINKEDIN",
    "B-LOCATION",
    "B-NAME",
    "B-PHONE",
    "B-PROFESSION",
    "B-SKILL",
    "B-WEBSITE",
    "I-CERTIFICATION",
    "I-CITY",
    "I-COUNTRY",
    "I-EDU_DEGREE",
    "I-EDU_UNIVERSITY",
    "I-EXP_COMPANY",
    "I-EXP_POSITION",
    "I-LANGUAGE",
    "I-LINKEDIN",
    "I-LOCATION",
    "I-NAME",
    "I-PHONE",
    "I-PROFESSION",
    "I-SKILL",
    "I-WEBSITE"
  ],
  "model_kind": "token_logistic_regression",
  "warning": "This is a weak-label baseline trained from corrected labels when available and AI labels otherwise. It is not a production LayoutLM model."
}