production-error-analysis-weak-ner
token_logistic_regression · corrected_then_ai · Completed ·
48 samples · 1569 spans
0.3705Token F1
0.1728Span F1
127Unmatched labels
10Test CVs
Field-Level Scores
| Field | Precision | Recall | F1 | Errors |
|---|---|---|---|---|
| contact | 0.4298 | 0.7313 | 0.5414 | FP 65 · FN 18 |
| location | 0.2623 | 0.2963 | 0.2783 | FP 45 · FN 38 |
| skills | 0.255 | 0.7525 | 0.381 | FP 666 · FN 75 |
| education | 0.3931 | 0.5889 | 0.4715 | FP 230 · FN 104 |
| employment | 0.3442 | 0.753 | 0.4725 | FP 482 · FN 83 |
Unmatched Label Types
| Label | Count |
|---|---|
| EXP_POSITION | 22 |
| COUNTRY | 17 |
| EDU_DEGREE | 16 |
| SKILL | 15 |
| CITY | 14 |
| EXP_COMPANY | 12 |
| CERTIFICATION | 10 |
| EDU_UNIVERSITY | 7 |
| PHONE | 6 |
| 3 | |
| NAME | 2 |
| PROFESSION | 2 |
| LOCATION | 1 |
Worst Test Samples
| Sample | Span F1 | Counts | False Negatives | False Positives |
|---|---|---|---|---|
|
A_K_Dwivedi_336829.pdf
Sample 6 · corrected
|
0.0333 | Gold 29 · Pred 331 · FN 23 · FP 325 |
COUNTRY: Kuwait
EDU_DEGREE: A.M.I.E. B.E. Mechanical Engineering
EDU_UNIVERSITY: I.E.R.T. Allahabad
EXP_COMPANY: M/s. BURGAN DRILLING COMPANY
EXP_COMPANY: M/S JASSIM TRANSPORT & STEVEDORING Co. WLL
EXP_COMPANY: M/S AL-IRSHAD GEN. TRADING & CONT. COMPANY
EXP_COMPANY: M/S SHAHEEN AL- GHANIM , ROAD AND BRIDGE CONST. Co.
EXP_COMPANY: M/S HALLIBURTON OVERSEAS LTD
EXP_COMPANY: M/S GAJRA BEVEL GRARS LTD.
EXP_COMPANY: M/S WEAVER TRACKS PVT LTD
EXP_COMPANY: M/S TATA ENGINEERING & LOCOMOTIVE CO. LTD
EXP_POSITION: Fleet Maintenance Manager
|
CERTIFICATION: Minimum
CERTIFICATION: driving
CERTIFICATION: CC8800-2200
CERTIFICATION: )
CERTIFICATION: Safety , Health
CERTIFICATION: Productivity
CERTIFICATION: Safety
CERTIFICATION: Organization
CERTIFICATION: safety
CERTIFICATION: (
CERTIFICATION: 2011
CERTIFICATION: (
|
|
CV_Lajmi_2022.docx
Sample 26 · corrected
|
0.0457 | Gold 47 · Pred 172 · FN 42 · FP 167 |
CERTIFICATION: aerodrome certification audit
CERTIFICATION: Human factor training
CERTIFICATION: Safety Management System Module 1
CERTIFICATION: Occurence report system
CERTIFICATION: Risk assessment and Safety study
CERTIFICATION: Advanced Safety Study
CERTIFICATION: Safety trainer training
CERTIFICATION: Basic Security training
CERTIFICATION: GNS1 : Safety Managment System
CERTIFICATION: Security of cargo and mail
CERTIFICATION: GSN 3- Emergency Planning and crisis management
CERTIFICATION: GSN 2 - Airside Safety & Operations
|
CERTIFICATION: AUTHORITY
CERTIFICATION: ( OPERATED BY CIVIL
CERTIFICATION: )
CERTIFICATION: (
CERTIFICATION: )
CERTIFICATION: Safety
CERTIFICATION: Safety AGA
CERTIFICATION: safety
CERTIFICATION: safety
CERTIFICATION: safety
CERTIFICATION: (
CERTIFICATION: ) Safety
|
|
Resume_Maheshkumar_CACPA_Bcom.pdf
Sample 34 · corrected
|
0.0707 | Gold 38 · Pred 160 · FN 31 · FP 153 |
CERTIFICATION: Certified Public Accountant ( CPA )
EDU_DEGREE: Chartered Accountancy
EDU_DEGREE: Company Secretary executive
EDU_UNIVERSITY: CPA Australia , Australia
EDU_UNIVERSITY: Institute of Chartered Accountants of India ( ICAI ) , India
EDU_UNIVERSITY: MG University , India
EDU_UNIVERSITY: Institute of Company Secretaries of India ( ICSI )
EXP_COMPANY: Magna Tyres Group , UAE
EXP_COMPANY: Mills Trading LLC , UAE
EXP_COMPANY: Agro Indus Credits Limited , India
EXP_COMPANY: G Joseph & Associates , Chartered Accountants , India
EXP_POSITION: Finance Manager
|
CERTIFICATION: 2015 Certified
CERTIFICATION: ( CPA )
CERTIFICATION: Institute
CERTIFICATION: ICAI
CERTIFICATION: (
CERTIFICATION: )
CERTIFICATION: (
CERTIFICATION: (
CERTIFICATION: audits
CERTIFICATION: 1
CERTIFICATION: Driving License
CERTIFICATION: Institute
|
|
344_MUHAMMAD_JC-40_1.pdf
Sample 20 · ai
|
0.0714 | Gold 13 · Pred 71 · FN 10 · FP 68 |
EDU_DEGREE: Education type : Bachelors
EDU_DEGREE: Education : Degree
EDU_UNIVERSITY: Education : Degree
EDU_UNIVERSITY: Specialization : Information Technology , Electrical , Electrical ,
EDU_UNIVERSITY: Job :
EDU_UNIVERSITY: Offer :
EDU_UNIVERSITY: Country : Algeria
EDU_UNIVERSITY: What is the meaning of below tags
EDU_UNIVERSITY: System :
EDU_UNIVERSITY: Email signature :
|
CERTIFICATION: Basic
CERTIFICATION: )
CERTIFICATION: 5000 60000
CERTIFICATION: (
CERTIFICATION: )
CERTIFICATION: 36000
CERTIFICATION: (
CERTIFICATION: )
CERTIFICATION: 24000
COUNTRY: JC-40
EDU_DEGREE: Specialization
EDU_DEGREE: Other
|
|
Arsh_CV_V2.pdf
Sample 23 · corrected
|
0.1584 | Gold 39 · Pred 163 · FN 23 · FP 147 |
CITY: Dubai
COUNTRY: UAE
EDU_DEGREE: Computer Science Engineering
EDU_UNIVERSITY: Indian Institute of Technology , Bombay , India
EDU_UNIVERSITY: Canadian University of Dubai , Dubai , UAE
EDU_UNIVERSITY: Board of Higher Secondary Education , Hyderabad , India
EXP_COMPANY: Grand Optics LLC
EXP_COMPANY: Al Khatib Properties LLC
EXP_COMPANY: Marine Registration Services LLC
EXP_POSITION: Project Manager
LOCATION: Port Saeed
NAME: Arshad Syed
|
CERTIFICATION: &
CERTIFICATION: ,
CERTIFICATION: 2015
CERTIFICATION: Indian
CERTIFICATION: Institute
CERTIFICATION: - 2015
CERTIFICATION: - 2011
CERTIFICATION: 2014
CERTIFICATION: 2012
CERTIFICATION: Interest
CERTIFICATION: Servers
CERTIFICATION: Training Development
|
|
Ahmed_Awad.docx
Sample 50 · corrected
|
0.2298 | Gold 34 · Pred 201 · FN 7 · FP 174 |
EDU_DEGREE: A2 Level
EDU_UNIVERSITY: Shorefields Comprehensive School
EXP_COMPANY: STRATA
EXP_COMPANY: University of Liverpool
EXP_COMPANY: University of Liverpool
LOCATION: Al Manara Tower
SKILL: Communication
|
CERTIFICATION: Quality Management System
CERTIFICATION: Auditor
CERTIFICATION: ,
CERTIFICATION: Quality Management System ( QMS )
CERTIFICATION: Quality Management System Auditor/Lead Auditor certified by the IRCA
CERTIFICATION: ISO 9000
CERTIFICATION: ISO 9001
CERTIFICATION: ISO
CERTIFICATION: Institute of Leadership and Management Endorsed Award certified by ILM.
CERTIFICATION: EPSRC.
CERTIFICATION: Internal Auditor ( OHSAS 18001 Series Standards ) ,
CERTIFICATION: ISO 9000 : 2000 FOUNDATION
|
|
JESSA_BUNAGAN_NEWW.pdf
Sample 32 · corrected
|
0.2474 | Gold 30 · Pred 67 · FN 18 · FP 55 |
EDU_DEGREE: High School Diploma
EDU_DEGREE: Elementary Diploma
EDU_UNIVERSITY: Cagayan State University
EDU_UNIVERSITY: Magalalag National High School
EDU_UNIVERSITY: Enrile East Central School Magalalag
EXP_COMPANY: Saudia Hypermarket Qatar
EXP_COMPANY: Asa Philippines Foundation Inc.
EXP_COMPANY: ACTIVE COOPERATION FOR ECONOMIC SUSTENANCE MULTI-PURPOSE COOPERATIVE
EXP_COMPANY: SM HYPER MARKET CHERRY CONGRESIONAL
EXP_POSITION: Microfinance Officer
EXP_POSITION: Cashier
LANGUAGE: Tagalog
|
CERTIFICATION: MS Office
CERTIFICATION: Foundation
CERTIFICATION: Diploma
EDU_DEGREE: Tagalog
EDU_DEGREE: Hypermarket
EDU_DEGREE: Microfinance
EDU_DEGREE: –
EDU_DEGREE: other
EDU_DEGREE: ECONOMIC
EDU_DEGREE: other
EDU_DEGREE: –
EDU_DEGREE: other
|
|
Rakshani-CV.docx
Sample 8 · corrected
|
0.2933 | Gold 29 · Pred 46 · FN 18 · FP 35 |
COUNTRY: Indian
EDU_DEGREE: Pursuing graduation
EDU_DEGREE: higher secondary
EDU_UNIVERSITY: Sant Gadge Baba University
EDU_UNIVERSITY: Holy Cross High School , Amravati.
EXP_COMPANY: Ashoka Hotel – Nagpur
EXP_COMPANY: Vastusankalp Group – Mumbai
EXP_COMPANY: Morpheus Consultancy – Mumbai
EXP_POSITION: Property Consultant
EXP_POSITION: HR Consultant/Recruiter
LOCATION: Bhanji house
LOCATION: Yari road
|
CERTIFICATION: (
CERTIFICATION: Mumbai (
CERTIFICATION: Mumbai (
CERTIFICATION: )
EDU_DEGREE: in
EDU_DEGREE: higher secondary from
EDU_DEGREE: Consultancy –
EDU_DEGREE: LANGUAGES
EDU_UNIVERSITY: Mumbai
EDU_UNIVERSITY: Baba University
EDU_UNIVERSITY: High School ,
EXP_COMPANY: VITAE
|
|
Khyati_Mayur_Trivedi_-_CV.docx
Sample 13 · corrected
|
0.4 | Gold 40 · Pred 150 · FN 2 · FP 112 |
EXP_POSITION: Business Development Manager
PHONE: ( +971 ) 565 320 905
|
CERTIFICATION: Training
CERTIFICATION: , 2014
CERTIFICATION: 2015
CERTIFICATION: , 2014
CERTIFICATION: 2011
CERTIFICATION: (
CERTIFICATION: Training
CERTIFICATION: (
CERTIFICATION: Training
CERTIFICATION: 2015
CERTIFICATION: Language
CERTIFICATION: Language
|
|
Sarang_O_original_-_Copy.pdf
Sample 35 · ai
|
0.4247 | Gold 35 · Pred 111 · FN 4 · FP 80 |
SKILL: Incoterms
SKILL: Contractual Knowledge
SKILL: Team leader
SKILL: CRM
|
CERTIFICATION: (
CERTIFICATION: )
CERTIFICATION: MS
CERTIFICATION: NTPC (
CERTIFICATION: )
EDU_DEGREE: major
EDU_DEGREE: ( Engineering
EDU_UNIVERSITY: Analysis
EDU_UNIVERSITY: Analysis
EXP_COMPANY: ,
EXP_COMPANY: &
EXP_COMPANY: &
|
Weak Labels Not Found In CV Text
| Sample | Count | Labels |
|---|---|---|
|
Neethu_Gopi.pdf
Sample 42 · corrected
|
14 |
EDU_UNIVERSITY: College of Pharmaceutical Sciences, Govt. Medical college, Thiruvananthapuram, India
EXP_POSITION: Role : Accurately dispensing drugs to patients according to a doctor's prescription
EDU_UNIVERSITY: College of Pharmaceutical Sciences, Govt. Medical college, Thiruvananthapuram
EDU_UNIVERSITY: Board of Higher secondary Examination, Kerala, India
LINKEDIN: https://www.linkedin.com/in/neethu-gopi-8a8b4179
SKILL: Review Prescriptions And Patient Counseling
EDU_UNIVERSITY: Secondary School Examination, Kerala, India
SKILL: Customer Service And Communication Skills
EXP_COMPANY: Delight Medicals, Kottayam, Kerala
EXP_COMPANY: Aparna Medicals, Kottayam, Kerala
SKILL: Pharmacy Operations Management
SKILL: Pharmacy Benefits Management
SKILL: Drug Interaction Assessment
COUNTRY: United Arab Emirates
|
|
Firas_CV__Jan_2023-_Online.docx
Sample 31 · corrected
|
9 |
CERTIFICATION: MCTS Microsoft Certified Technology Specialist, Windows 7 - April 2015, Microsoft IT Academy
CERTIFICATION: Mini MBA Certificate - May 2016, PRICEWATERHOUSECOOPER Academy, Abu Dhabi
CERTIFICATION: Microsoft Certified Professional MCP - April 2015, Microsoft IT Academy
CERTIFICATION: MCTS Microsoft Project 2010 - June 2015, Microsoft IT Academy
CERTIFICATION: Microsoft Specialist - January 2015, Microsoft IT Academy
EXP_COMPANY: Ministry of Presidential Affairs / Camel Race Division
EXP_COMPANY: Ministry of Presidential Affairs / Camel Race Division
EXP_COMPANY: Ministry of Presidential Affairs / Camel Race Division
PROFESSION: Information Technology Manager, IT Project Manager
|
|
Resume_Maheshkumar_CACPA_Bcom.pdf
Sample 34 · corrected
|
5 |
EDU_DEGREE: Certified Public Accountant (CPA)
SKILL: Financial Planning & Analysis
EDU_DEGREE: Bachelor of Commerce (B.Com)
CERTIFICATION: Chartered Accountant (ICAI)
SKILL: Budgeting
|
|
cv11.pdf
Sample 25 · corrected
|
5 |
EDU_UNIVERSITY: DUBAI MODERN EDUCATION SCHOOL
SKILL: PREPARATION AND ORGANIZATION
COUNTRY: United Arab Emirates
PROFESSION: Legal Professional
SKILL: PROBLEM SOLVING
|
|
CV_Khrystyna.pdf
Sample 29 · corrected
|
5 |
EXP_POSITION: Personal assistant in non-commercial organization
EDU_DEGREE: Intensive course of French Language
EDU_DEGREE: EASA CC Attestation
CITY: Dubai
COUNTRY: UAE
|
|
Sarang_O_original_-_Copy.pdf
Sample 35 · ai
|
4 |
SKILL: MS Office
LOCATION: Dubai
CITY: Dubai
COUNTRY: UAE
|
|
CV_Lajmi_2022.docx
Sample 26 · corrected
|
4 |
EDU_DEGREE: Air Navigation, Rank of second lieutenant
CERTIFICATION: Safety Management System implementation
EXP_COMPANY: BORJ EL AMRI AVIATION ACADEMY
EXP_POSITION: General Manager East Africa
|
|
Ahmed_Awad.docx
Sample 50 · corrected
|
4 |
EDU_DEGREE: BEng in Engineering (Hons), specialised in Aerospace Materials Engineering
EDU_DEGREE: PhD in Engineering, specialised in Materials and Electronics Engineering
EXP_POSITION: Project Management
COUNTRY: UAE
|
|
A_Mohamed_Ansari_309761.pdf
Sample 5 · corrected
|
4 |
EDU_UNIVERSITY: National Institute of Construction Management and Research, Pune
EXP_COMPANY: Higgs & Hill Qatar (wll) (Royal BAM Group, Netherlands’)
EDU_DEGREE: Bachelor of Engineering in Civil Engineering
EDU_DEGREE: Certificate in CADD Rel.14
|
|
9_CV_Obaid.pdf
Sample 3 · corrected
|
4 |
EXP_POSITION: Assistant Legal Advisor, Legislation Committee
EXP_POSITION: Lawyer
EXP_POSITION: Lawyer
EXP_POSITION: Lawyer
|
|
Khyati_Mayur_Trivedi_-_CV.docx
Sample 11 · corrected
|
4 |
EXP_POSITION: Business Development / Sales, Marketing Manager & Global Recruiter
EXP_COMPANY: VAIBHAV LOAN SOLUTIONS & SERVICES – India
EXP_COMPANY: F.GHEEWALA- ZTECH MANPOWER SERVICES, UAE
PHONE: +971 565 320 905
|
|
Arsh_CV_V2.pdf
Sample 23 · corrected
|
3 |
EDU_DEGREE: Artificial Intelligence & Robotics Engineering
CERTIFICATION: Entrepreneurship, June 2018, Dubai, UAE
CERTIFICATION: Digital Marketing, May 2016, Dubai, UAE
|
|
ABDALLAH_KOURRI_CV_Apr2022.docx
Sample 27 · ai
|
3 |
EXP_COMPANY: Quebecor- Mediapages (Vidétron)
EDU_DEGREE: Master – Business Intelligence
SKILL: Data Analysis
|
|
Ahmed_Awad.docx
Sample 40 · corrected
|
3 |
COUNTRY: United Arab Emirates
EXP_POSITION: Project Management
CITY: Al Ain
|
|
Ashik_Mankarathodi_original.pdf
Sample 4 · corrected
|
3 |
LINKEDIN: https://www.linkedin.com/in/ashik-mankarathodi
CITY: Dubai
SKILL: Excel
|
|
A_S_Shahul_Hameed_296384.pdf
Sample 17 · corrected
|
3 |
PHONE: +971559040029
PHONE: +919841092515
COUNTRY: UAE, India
|
|
Anwar_Shaikh_Abbas.docx
Sample 14 · corrected
|
3 |
CERTIFICATION: Jotun Paints – Oman for Internal/External Painting Systems
PHONE: 050 1097929
CITY: Abudhabi
|
|
nelmina-domingo.pdf
Sample 21 · corrected
|
3 |
NAME: Nelmina Domingo
EXP_POSITION: Store Assistant
CITY: Dubai
|
|
ResumeMuhammadTariqNaseer.pdf
Sample 19 · corrected
|
3 |
COUNTRY: United Arab Emirates
EDU_UNIVERSITY: Awards
CITY: Dubai
|
|
344_MUHAMMAD_JC-40_1.pdf
Sample 20 · ai
|
2 |
NAME: MUHAMMAD ZUBAIR
EDU_DEGREE: Degree
|
|
Khyati_Mayur_Trivedi_-_CV.docx
Sample 13 · corrected
|
2 |
EXP_COMPANY: VAIBHAV LOAN SOLUTIONS & SERVICES – India
EXP_COMPANY: F.GHEEWALA- ZTECH MANPOWER SERVICES, UAE
|
|
Anwar_Shaikh_Abbas.docx
Sample 15 · corrected
|
2 |
PHONE: 050 1097929
CITY: Abudhabi
|
|
Hamza_Tawa_Resume_1_8rnqKiL.pdf
Sample 18 · corrected
|
2 |
EXP_POSITION: Investment Banking Analyst | M&A and Valuation Advisory
EDU_DEGREE: Cleared CFA Level 1
|
|
Khyati_Mayur_Trivedi_-_CV.docx
Sample 10 · corrected
|
2 |
EXP_POSITION: Business Development / Sales, Marketing Manager & Global Recruiter
COUNTRY: UAE
|
|
OLGA_PAPADOPOULOU_CV_3_1.pdf
Sample 22 · corrected
|
2 |
SKILL: HTML
SKILL: CSS
|
Raw Metrics
{
"token_entity_precision": 0.2712,
"token_entity_recall": 0.5844,
"token_entity_f1": 0.3705,
"span_precision": 0.106,
"span_recall": 0.4671,
"span_f1": 0.1728,
"gold_span_count": 334,
"predicted_span_count": 1472,
"field_metrics": [
{
"field": "contact",
"precision": 0.4298,
"recall": 0.7313,
"f1": 0.5414,
"tp": 49,
"fp": 65,
"fn": 18
},
{
"field": "location",
"precision": 0.2623,
"recall": 0.2963,
"f1": 0.2783,
"tp": 16,
"fp": 45,
"fn": 38
},
{
"field": "skills",
"precision": 0.255,
"recall": 0.7525,
"f1": 0.381,
"tp": 228,
"fp": 666,
"fn": 75
},
{
"field": "education",
"precision": 0.3931,
"recall": 0.5889,
"f1": 0.4715,
"tp": 149,
"fp": 230,
"fn": 104
},
{
"field": "employment",
"precision": 0.3442,
"recall": 0.753,
"f1": 0.4725,
"tp": 253,
"fp": 482,
"fn": 83
}
],
"worst_samples": [
{
"sample_id": 6,
"file_name": "A_K_Dwivedi_336829.pdf",
"label_source": "corrected",
"gold_span_count": 29,
"predicted_span_count": 331,
"false_positive_count": 325,
"false_negative_count": 23,
"token_error_count": 403,
"span_precision": 0.0181,
"span_recall": 0.2069,
"span_f1": 0.0333,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "Minimum",
"start_token": 60,
"end_token": 61
},
{
"label": "CERTIFICATION",
"text": "driving",
"start_token": 111,
"end_token": 112
},
{
"label": "CERTIFICATION",
"text": "CC8800-2200",
"start_token": 171,
"end_token": 172
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 310,
"end_token": 311
},
{
"label": "CERTIFICATION",
"text": "Safety , Health",
"start_token": 334,
"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": "Organization",
"start_token": 532,
"end_token": 533
},
{
"label": "CERTIFICATION",
"text": "safety",
"start_token": 791,
"end_token": 792
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 879,
"end_token": 880
},
{
"label": "CERTIFICATION",
"text": "2011",
"start_token": 911,
"end_token": 912
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 998,
"end_token": 999
}
],
"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 HALLIBURTON OVERSEAS LTD",
"start_token": 1296,
"end_token": 1300
},
{
"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": "Fleet Maintenance Manager",
"start_token": 665,
"end_token": 668
}
]
},
{
"sample_id": 26,
"file_name": "CV_Lajmi_2022.docx",
"label_source": "corrected",
"gold_span_count": 47,
"predicted_span_count": 172,
"false_positive_count": 167,
"false_negative_count": 42,
"token_error_count": 229,
"span_precision": 0.0291,
"span_recall": 0.1064,
"span_f1": 0.0457,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "AUTHORITY",
"start_token": 58,
"end_token": 59
},
{
"label": "CERTIFICATION",
"text": "( OPERATED BY CIVIL",
"start_token": 73,
"end_token": 77
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 81,
"end_token": 82
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 109,
"end_token": 110
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 118,
"end_token": 119
},
{
"label": "CERTIFICATION",
"text": "Safety",
"start_token": 144,
"end_token": 145
},
{
"label": "CERTIFICATION",
"text": "Safety AGA",
"start_token": 148,
"end_token": 150
},
{
"label": "CERTIFICATION",
"text": "safety",
"start_token": 158,
"end_token": 159
},
{
"label": "CERTIFICATION",
"text": "safety",
"start_token": 194,
"end_token": 195
},
{
"label": "CERTIFICATION",
"text": "safety",
"start_token": 226,
"end_token": 227
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 262,
"end_token": 263
},
{
"label": "CERTIFICATION",
"text": ") Safety",
"start_token": 271,
"end_token": 273
}
],
"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": "Safety trainer training",
"start_token": 643,
"end_token": 646
},
{
"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
}
]
},
{
"sample_id": 34,
"file_name": "Resume_Maheshkumar_CACPA_Bcom.pdf",
"label_source": "corrected",
"gold_span_count": 38,
"predicted_span_count": 160,
"false_positive_count": 153,
"false_negative_count": 31,
"token_error_count": 183,
"span_precision": 0.0437,
"span_recall": 0.1842,
"span_f1": 0.0707,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "2015 Certified",
"start_token": 15,
"end_token": 17
},
{
"label": "CERTIFICATION",
"text": "( CPA )",
"start_token": 19,
"end_token": 22
},
{
"label": "CERTIFICATION",
"text": "Institute",
"start_token": 28,
"end_token": 29
},
{
"label": "CERTIFICATION",
"text": "ICAI",
"start_token": 35,
"end_token": 36
},
{
"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": "(",
"start_token": 135,
"end_token": 136
},
{
"label": "CERTIFICATION",
"text": "audits",
"start_token": 372,
"end_token": 373
},
{
"label": "CERTIFICATION",
"text": "1",
"start_token": 408,
"end_token": 409
},
{
"label": "CERTIFICATION",
"text": "Driving License",
"start_token": 412,
"end_token": 414
},
{
"label": "CERTIFICATION",
"text": "Institute",
"start_token": 420,
"end_token": 421
}
],
"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": "MG University , India",
"start_token": 45,
"end_token": 49
},
{
"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
}
]
},
{
"sample_id": 20,
"file_name": "344_MUHAMMAD_JC-40_1.pdf",
"label_source": "ai",
"gold_span_count": 13,
"predicted_span_count": 71,
"false_positive_count": 68,
"false_negative_count": 10,
"token_error_count": 112,
"span_precision": 0.0423,
"span_recall": 0.2308,
"span_f1": 0.0714,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "Basic",
"start_token": 408,
"end_token": 409
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 415,
"end_token": 416
},
{
"label": "CERTIFICATION",
"text": "5000 60000",
"start_token": 419,
"end_token": 421
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 425,
"end_token": 426
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 428,
"end_token": 429
},
{
"label": "CERTIFICATION",
"text": "36000",
"start_token": 434,
"end_token": 435
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 439,
"end_token": 440
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 442,
"end_token": 443
},
{
"label": "CERTIFICATION",
"text": "24000",
"start_token": 448,
"end_token": 449
},
{
"label": "COUNTRY",
"text": "JC-40",
"start_token": 231,
"end_token": 232
},
{
"label": "EDU_DEGREE",
"text": "Specialization",
"start_token": 59,
"end_token": 60
},
{
"label": "EDU_DEGREE",
"text": "Other",
"start_token": 111,
"end_token": 112
}
],
"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": 23,
"file_name": "Arsh_CV_V2.pdf",
"label_source": "corrected",
"gold_span_count": 39,
"predicted_span_count": 163,
"false_positive_count": 147,
"false_negative_count": 23,
"token_error_count": 175,
"span_precision": 0.0982,
"span_recall": 0.4103,
"span_f1": 0.1584,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "&",
"start_token": 62,
"end_token": 63
},
{
"label": "CERTIFICATION",
"text": ",",
"start_token": 71,
"end_token": 72
},
{
"label": "CERTIFICATION",
"text": "2015",
"start_token": 112,
"end_token": 113
},
{
"label": "CERTIFICATION",
"text": "Indian",
"start_token": 115,
"end_token": 116
},
{
"label": "CERTIFICATION",
"text": "Institute",
"start_token": 116,
"end_token": 117
},
{
"label": "CERTIFICATION",
"text": "- 2015",
"start_token": 127,
"end_token": 129
},
{
"label": "CERTIFICATION",
"text": "- 2011",
"start_token": 143,
"end_token": 145
},
{
"label": "CERTIFICATION",
"text": "2014",
"start_token": 207,
"end_token": 208
},
{
"label": "CERTIFICATION",
"text": "2012",
"start_token": 219,
"end_token": 220
},
{
"label": "CERTIFICATION",
"text": "Interest",
"start_token": 266,
"end_token": 267
},
{
"label": "CERTIFICATION",
"text": "Servers",
"start_token": 299,
"end_token": 300
},
{
"label": "CERTIFICATION",
"text": "Training Development",
"start_token": 306,
"end_token": 308
}
],
"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": "Project Manager",
"start_token": 199,
"end_token": 201
},
{
"label": "LOCATION",
"text": "Port Saeed",
"start_token": 105,
"end_token": 107
},
{
"label": "NAME",
"text": "Arshad Syed",
"start_token": 0,
"end_token": 2
}
]
},
{
"sample_id": 50,
"file_name": "Ahmed_Awad.docx",
"label_source": "corrected",
"gold_span_count": 34,
"predicted_span_count": 201,
"false_positive_count": 174,
"false_negative_count": 7,
"token_error_count": 292,
"span_precision": 0.1343,
"span_recall": 0.7941,
"span_f1": 0.2298,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "Quality Management System",
"start_token": 47,
"end_token": 50
},
{
"label": "CERTIFICATION",
"text": "Auditor",
"start_token": 51,
"end_token": 52
},
{
"label": "CERTIFICATION",
"text": ",",
"start_token": 117,
"end_token": 118
},
{
"label": "CERTIFICATION",
"text": "Quality Management System ( QMS )",
"start_token": 264,
"end_token": 270
},
{
"label": "CERTIFICATION",
"text": "Quality Management System Auditor/Lead Auditor certified by the IRCA",
"start_token": 326,
"end_token": 335
},
{
"label": "CERTIFICATION",
"text": "ISO 9000",
"start_token": 337,
"end_token": 339
},
{
"label": "CERTIFICATION",
"text": "ISO 9001",
"start_token": 342,
"end_token": 344
},
{
"label": "CERTIFICATION",
"text": "ISO",
"start_token": 347,
"end_token": 348
},
{
"label": "CERTIFICATION",
"text": "Institute of Leadership and Management Endorsed Award certified by ILM.",
"start_token": 359,
"end_token": 369
},
{
"label": "CERTIFICATION",
"text": "EPSRC.",
"start_token": 396,
"end_token": 397
},
{
"label": "CERTIFICATION",
"text": "Internal Auditor ( OHSAS 18001 Series Standards ) ,",
"start_token": 412,
"end_token": 421
},
{
"label": "CERTIFICATION",
"text": "ISO 9000 : 2000 FOUNDATION",
"start_token": 421,
"end_token": 426
}
],
"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": "EXP_COMPANY",
"text": "University of Liverpool",
"start_token": 1574,
"end_token": 1577
},
{
"label": "EXP_COMPANY",
"text": "University of Liverpool",
"start_token": 1707,
"end_token": 1710
},
{
"label": "LOCATION",
"text": "Al Manara Tower",
"start_token": 5,
"end_token": 8
},
{
"label": "SKILL",
"text": "Communication",
"start_token": 631,
"end_token": 632
}
]
},
{
"sample_id": 32,
"file_name": "JESSA_BUNAGAN_NEWW.pdf",
"label_source": "corrected",
"gold_span_count": 30,
"predicted_span_count": 67,
"false_positive_count": 55,
"false_negative_count": 18,
"token_error_count": 58,
"span_precision": 0.1791,
"span_recall": 0.4,
"span_f1": 0.2474,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "MS Office",
"start_token": 33,
"end_token": 35
},
{
"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": "Hypermarket",
"start_token": 142,
"end_token": 143
},
{
"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": "other",
"start_token": 234,
"end_token": 235
},
{
"label": "EDU_DEGREE",
"text": "ECONOMIC",
"start_token": 252,
"end_token": 253
},
{
"label": "EDU_DEGREE",
"text": "other",
"start_token": 279,
"end_token": 280
},
{
"label": "EDU_DEGREE",
"text": "–",
"start_token": 317,
"end_token": 318
},
{
"label": "EDU_DEGREE",
"text": "other",
"start_token": 338,
"end_token": 339
}
],
"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": "Magalalag National High School",
"start_token": 390,
"end_token": 394
},
{
"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
}
]
},
{
"sample_id": 8,
"file_name": "Rakshani-CV.docx",
"label_source": "corrected",
"gold_span_count": 29,
"predicted_span_count": 46,
"false_positive_count": 35,
"false_negative_count": 18,
"token_error_count": 63,
"span_precision": 0.2391,
"span_recall": 0.3793,
"span_f1": 0.2933,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 112,
"end_token": 113
},
{
"label": "CERTIFICATION",
"text": "Mumbai (",
"start_token": 149,
"end_token": 151
},
{
"label": "CERTIFICATION",
"text": "Mumbai (",
"start_token": 205,
"end_token": 207
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 211,
"end_token": 212
},
{
"label": "EDU_DEGREE",
"text": "in",
"start_token": 52,
"end_token": 53
},
{
"label": "EDU_DEGREE",
"text": "higher secondary from",
"start_token": 87,
"end_token": 90
},
{
"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": "Baba University",
"start_token": 82,
"end_token": 84
},
{
"label": "EDU_UNIVERSITY",
"text": "High School ,",
"start_token": 99,
"end_token": 102
},
{
"label": "EXP_COMPANY",
"text": "VITAE",
"start_token": 1,
"end_token": 2
}
],
"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_UNIVERSITY",
"text": "Sant Gadge Baba University",
"start_token": 80,
"end_token": 84
},
{
"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
},
{
"label": "LOCATION",
"text": "Bhanji house",
"start_token": 29,
"end_token": 31
},
{
"label": "LOCATION",
"text": "Yari road",
"start_token": 32,
"end_token": 34
}
]
},
{
"sample_id": 13,
"file_name": "Khyati_Mayur_Trivedi_-_CV.docx",
"label_source": "corrected",
"gold_span_count": 40,
"predicted_span_count": 150,
"false_positive_count": 112,
"false_negative_count": 2,
"token_error_count": 148,
"span_precision": 0.2533,
"span_recall": 0.95,
"span_f1": 0.4,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "Training",
"start_token": 633,
"end_token": 634
},
{
"label": "CERTIFICATION",
"text": ", 2014",
"start_token": 655,
"end_token": 657
},
{
"label": "CERTIFICATION",
"text": "2015",
"start_token": 661,
"end_token": 662
},
{
"label": "CERTIFICATION",
"text": ", 2014",
"start_token": 713,
"end_token": 715
},
{
"label": "CERTIFICATION",
"text": "2011",
"start_token": 826,
"end_token": 827
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 1095,
"end_token": 1096
},
{
"label": "CERTIFICATION",
"text": "Training",
"start_token": 1211,
"end_token": 1212
},
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 1269,
"end_token": 1270
},
{
"label": "CERTIFICATION",
"text": "Training",
"start_token": 1385,
"end_token": 1386
},
{
"label": "CERTIFICATION",
"text": "2015",
"start_token": 1432,
"end_token": 1433
},
{
"label": "CERTIFICATION",
"text": "Language",
"start_token": 1553,
"end_token": 1554
},
{
"label": "CERTIFICATION",
"text": "Language",
"start_token": 1564,
"end_token": 1565
}
],
"false_negatives": [
{
"label": "EXP_POSITION",
"text": "Business Development Manager",
"start_token": 1454,
"end_token": 1457
},
{
"label": "PHONE",
"text": "( +971 ) 565 320 905",
"start_token": 6,
"end_token": 12
}
]
},
{
"sample_id": 35,
"file_name": "Sarang_O_original_-_Copy.pdf",
"label_source": "ai",
"gold_span_count": 35,
"predicted_span_count": 111,
"false_positive_count": 80,
"false_negative_count": 4,
"token_error_count": 98,
"span_precision": 0.2793,
"span_recall": 0.8857,
"span_f1": 0.4247,
"false_positives": [
{
"label": "CERTIFICATION",
"text": "(",
"start_token": 265,
"end_token": 266
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 273,
"end_token": 274
},
{
"label": "CERTIFICATION",
"text": "MS",
"start_token": 529,
"end_token": 530
},
{
"label": "CERTIFICATION",
"text": "NTPC (",
"start_token": 569,
"end_token": 571
},
{
"label": "CERTIFICATION",
"text": ")",
"start_token": 578,
"end_token": 579
},
{
"label": "EDU_DEGREE",
"text": "major",
"start_token": 100,
"end_token": 101
},
{
"label": "EDU_DEGREE",
"text": "( Engineering",
"start_token": 234,
"end_token": 236
},
{
"label": "EDU_UNIVERSITY",
"text": "Analysis",
"start_token": 386,
"end_token": 387
},
{
"label": "EDU_UNIVERSITY",
"text": "Analysis",
"start_token": 452,
"end_token": 453
},
{
"label": "EXP_COMPANY",
"text": ",",
"start_token": 7,
"end_token": 8
},
{
"label": "EXP_COMPANY",
"text": "&",
"start_token": 117,
"end_token": 118
},
{
"label": "EXP_COMPANY",
"text": "&",
"start_token": 123,
"end_token": 124
}
],
"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
}
]
}
],
"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": 0.2045,
"recall": 0.36,
"f1": 0.2609,
"support": 25.0
},
"B-CITY": {
"precision": 1.0,
"recall": 0.3333,
"f1": 0.5,
"support": 3.0
},
"B-COUNTRY": {
"precision": 0.4,
"recall": 0.4,
"f1": 0.4,
"support": 5.0
},
"B-EDU_DEGREE": {
"precision": 0.36,
"recall": 0.4737,
"f1": 0.4091,
"support": 19.0
},
"B-EDU_UNIVERSITY": {
"precision": 0.32,
"recall": 0.4103,
"f1": 0.3596,
"support": 39.0
},
"B-EMAIL": {
"precision": 0.7,
"recall": 1.0,
"f1": 0.8235,
"support": 7.0
},
"B-EXP_COMPANY": {
"precision": 0.2838,
"recall": 0.525,
"f1": 0.3684,
"support": 40.0
},
"B-EXP_POSITION": {
"precision": 0.3333,
"recall": 0.5814,
"f1": 0.4237,
"support": 43.0
},
"B-LANGUAGE": {
"precision": 0.5909,
"recall": 0.9286,
"f1": 0.7222,
"support": 28.0
},
"B-LINKEDIN": {
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"support": 1.0
},
"B-LOCATION": {
"precision": 0.1702,
"recall": 0.4,
"f1": 0.2388,
"support": 20.0
},
"B-NAME": {
"precision": 0.2857,
"recall": 0.5,
"f1": 0.3636,
"support": 8.0
},
"B-PHONE": {
"precision": 0.35,
"recall": 0.4667,
"f1": 0.4,
"support": 15.0
},
"B-PROFESSION": {
"precision": 0.0909,
"recall": 0.1667,
"f1": 0.1176,
"support": 6.0
},
"B-SKILL": {
"precision": 0.2226,
"recall": 0.7973,
"f1": 0.3481,
"support": 74.0
},
"B-WEBSITE": {
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"support": 1.0
},
"I-CERTIFICATION": {
"precision": 0.2526,
"recall": 0.6729,
"f1": 0.3673,
"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": 0.2171,
"recall": 0.8085,
"f1": 0.3423,
"support": 47.0
},
"I-EDU_UNIVERSITY": {
"precision": 0.4961,
"recall": 0.4324,
"f1": 0.4621,
"support": 148.0
},
"I-EXP_COMPANY": {
"precision": 0.2576,
"recall": 0.6242,
"f1": 0.3647,
"support": 149.0
},
"I-EXP_POSITION": {
"precision": 0.3926,
"recall": 0.7356,
"f1": 0.512,
"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": 0.25,
"recall": 0.0769,
"f1": 0.1176,
"support": 26.0
},
"I-NAME": {
"precision": 0.1852,
"recall": 0.4167,
"f1": 0.2564,
"support": 12.0
},
"I-PHONE": {
"precision": 0.45,
"recall": 0.8571,
"f1": 0.5902,
"support": 21.0
},
"I-PROFESSION": {
"precision": 0.0392,
"recall": 0.1818,
"f1": 0.0645,
"support": 11.0
},
"I-SKILL": {
"precision": 0.1452,
"recall": 0.5217,
"f1": 0.2271,
"support": 69.0
},
"I-WEBSITE": {
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"support": 0.0
},
"micro avg": {
"precision": 0.2712,
"recall": 0.5844,
"f1": 0.3705,
"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."
}