Hugging Face's logo

poltextlab
/
xlm-roberta-large-pooled-cap-minor-v4

Text Classification
Transformers
Safetensors
English
Hungarian
xlm-roberta
roberta
Eval Results
Model card Files
xet
Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This model is gated. Please confirm intended use.

Log in or Sign Up to review the conditions and access this model content.

xlm-roberta-large-pooled-cap-minor-v4

How to use the model 

from transformers import AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
    model="poltextlab/xlm-roberta-large-pooled-cap-minor-v4",
    task="text-classification",
    tokenizer=tokenizer,
    use_fast=False,
    token="<your_hf_read_only_token>"
)

text = "<text_to_classify>"
pipe(text)

Classification Report

Overall Performance:

  • Accuracy: 87%
  • Macro Avg: Precision: 0.66, Recall: 0.58, F1-score: 0.60
  • Weighted Avg: Precision: 0.86, Recall: 0.87, F1-score: 0.86

Per-Class Metrics:

Label Precision Recall F1-score Support
100: Macroeconomics - General 0.6 0.5 0.55 725
101: Macroeconomics - Interest Rates 0.71 0.55 0.62 102
103: Macroeconomics - Unemployment Rate 0.58 0.46 0.51 211
104: Macroeconomics - Monetary Policy 0.65 0.56 0.6 301
105: Macroeconomics - National Budget 0.76 0.82 0.79 5184
107: Macroeconomics - Tax Code 0.74 0.68 0.71 1927
108: Macroeconomics - Industrial Policy 0.72 0.73 0.72 478
110: Macroeconomics - Price Control 0.66 0.61 0.63 150
199: Macroeconomics - Other 0 0 0 5
200: Civil Rights - General 0.68 0.6 0.64 424
201: Civil Rights - Minority Discrimination 0.76 0.68 0.72 479
202: Civil Rights - Gender Discrimination 0.79 0.71 0.75 229
204: Civil Rights - Age Discrimination 0.87 0.33 0.47 40
205: Civil Rights - Handicap Discrimination 0.67 0.64 0.66 76
206: Civil Rights - Voting Rights 0.69 0.63 0.66 182
207: Civil Rights - Freedom of Speech 0.69 0.57 0.62 236
208: Civil Rights - Right to Privacy 0.73 0.52 0.61 358
209: Civil Rights - Anti-Government 0.64 0.5 0.56 119
299: Civil Rights - Other 0.65 0.3 0.41 37
300: Health - General 0.71 0.57 0.63 525
301: Health - Health Care Reform 0.53 0.46 0.49 290
302: Health - Insurance 0.61 0.49 0.54 377
321: Health - Drug Industry 0.7 0.65 0.67 163
322: Health - Medical Facilities 0.79 0.77 0.78 279
323: Health - Insurance Providers 0.68 0.71 0.7 262
324: Health - Medical Liability 0.62 0.41 0.49 44
325: Health - Manpower 0.54 0.59 0.56 162
331: Health - Disease Prevention 0.73 0.74 0.74 247
332: Health - Infants and Children 0.59 0.72 0.65 111
333: Health - Mental Health 0.66 0.77 0.71 64
334: Health - Long-term Care 0.71 0.62 0.66 102
335: Health - Drug Coverage and Cost 0.78 0.66 0.71 64
341: Health - Tobacco Abuse 0.83 0.89 0.86 153
342: Health - Drug and Alcohol Abuse 0.6 0.65 0.63 147
398: Health - Research and Development 0.73 0.65 0.69 113
399: Health - Other 0 0 0 19
400: Agriculture - General 0.64 0.63 0.64 775
401: Agriculture - Trade 0.56 0.53 0.54 263
402: Agriculture - Subsidies to Farmers 0.65 0.71 0.68 561
403: Agriculture - Food Inspection & Safety 0.71 0.61 0.65 186
404: Agriculture - Food Marketing & Promotion 0.62 0.58 0.6 55
405: Agriculture - Animal and Crop Disease 0.82 0.72 0.76 151
408: Agriculture - Fisheries & Fishing 0.8 0.79 0.79 76
498: Agriculture - Research and Development 0.85 0.81 0.83 119
499: Agriculture - Other 0.67 0.58 0.62 265
500: Labor - General 0.66 0.56 0.6 307
501: Labor - Worker Safety 0.78 0.7 0.74 160
502: Labor - Employment Training 0.68 0.7 0.69 391
503: Labor - Employee Benefits 0.48 0.47 0.47 354
504: Labor - Labor Unions 0.74 0.63 0.68 455
505: Labor - Fair Labor Standards 0.55 0.42 0.47 250
506: Labor - Youth Employment 0.65 0.77 0.71 230
529: Labor - Migrant and Seasonal 0.54 0.48 0.51 92
599: Labor - Other 1 0.59 0.74 17
600: Education - General 0.74 0.61 0.67 356
601: Education - Higher 0.86 0.87 0.86 1370
602: Education - Elementary & Secondary 0.82 0.85 0.83 1616
603: Education - Underprivileged 0.51 0.4 0.45 87
604: Education - Vocational 0.8 0.85 0.82 358
606: Education - Special 0.86 0.72 0.79 61
607: Education - Excellence 0.56 0.52 0.54 94
698: Education - Research and Development 0.95 0.72 0.82 29
699: Education - Other 0.72 0.47 0.57 70
700: Environment - General 0.7 0.76 0.73 432
701: Environment - Drinking Water 0.69 0.55 0.61 106
703: Environment - Waste Disposal 0.76 0.83 0.79 266
704: Environment - Hazardous Waste 0.68 0.58 0.63 71
705: Environment - Air Pollution 0.76 0.71 0.73 204
707: Environment - Recycling 1 0.27 0.42 15
708: Environment - Indoor Hazards 0.5 0.08 0.14 12
709: Environment - Species & Forest 0.79 0.69 0.73 147
711: Environment - Land and Water Conservation 0.39 0.2 0.27 54
798: Environment - Research and Development 0 0 0 17
799: Environment - Other 0 0 0 14
800: Energy - General 0.66 0.53 0.59 211
801: Energy - Nuclear 0.74 0.74 0.74 190
802: Energy - Electricity 0.6 0.58 0.59 221
803: Energy - Natural Gas & Oil 0.61 0.73 0.66 328
805: Energy - Coal 0.77 0.8 0.78 84
806: Energy - Alternative & Renewable 0.58 0.54 0.56 82
807: Energy - Conservation 0.72 0.59 0.65 61
898: Energy - Research and Development 0 0 0 10
899: Energy - Other 0.4 0.09 0.15 22
900: Immigration 0.75 0.76 0.75 648
1000: Transportation - General 0.74 0.63 0.68 278
1001: Transportation - Mass 0.62 0.67 0.64 253
1002: Transportation - Highways 0.75 0.77 0.76 669
1003: Transportation - Air Travel 0.83 0.85 0.84 239
1005: Transportation - Railroad Travel 0.78 0.82 0.8 499
1007: Transportation - Maritime 0.85 0.82 0.84 350
1010: Transportation - Infrastructure 0.56 0.31 0.4 72
1098: Transportation - Research and Development 0 0 0 8
1099: Transportation - Other 1 0.07 0.13 14
1200: Law and Crime - General 0.73 0.61 0.66 339
1201: Law and Crime - Agencies 0.75 0.79 0.77 789
1202: Law and Crime - White Collar Crime 0.61 0.47 0.54 240
1203: Law and Crime - Illegal Drugs 0.65 0.62 0.64 120
1204: Law and Crime - Court Administration 0.71 0.77 0.74 1031
1205: Law and Crime - Prisons 0.69 0.7 0.7 212
1206: Law and Crime - Juvenile Crime 0.68 0.62 0.65 48
1207: Law and Crime - Child Abuse 0.68 0.61 0.64 90
1208: Law and Crime - Family Issues 0.7 0.58 0.63 339
1210: Law and Crime - Criminal & Civil Code 0.73 0.58 0.65 769
1211: Law and Crime - Crime Control 0.43 0.37 0.4 130
1227: Law and Crime - Police 0.5 0.21 0.3 28
1299: Law and Crime - Other 0.73 0.64 0.68 121
1300: Social Welfare - General 0.63 0.62 0.63 853
1302: Social Welfare - Low-Income Assistance 0.66 0.61 0.64 383
1303: Social Welfare - Elderly Assistance 0.71 0.63 0.67 567
1304: Social Welfare - Disabled Assistance 0.73 0.64 0.68 169
1305: Social Welfare - Volunteer Associations 0.65 0.66 0.66 164
1308: Social Welfare - Child Care 0.71 0.63 0.67 57
1399: Social Welfare - Other 1 0.5 0.67 22
1400: Housing - General 0.64 0.78 0.7 528
1401: Housing - Community Development 0.51 0.48 0.49 229
1403: Housing - Urban Development 0.47 0.62 0.53 239
1404: Housing - Rural Housing 0 0 0 9
1405: Housing - Rural Development 0.61 0.51 0.55 293
1406: Housing - Low-Income Assistance 0.56 0.64 0.6 215
1407: Housing - Veterans 0.61 0.69 0.65 16
1408: Housing - Elderly 0.79 0.48 0.59 23
1409: Housing - Homeless 0.75 0.84 0.79 97
1498: Housing - Research and Development 0 0 0 0
1499: Housing - Other 0 0 0 16
1500: Domestic Commerce - General 0.77 0.7 0.73 468
1501: Domestic Commerce - Banking 0.62 0.67 0.65 506
1502: Domestic Commerce - Securities & Commodities 0.62 0.52 0.57 116
1504: Domestic Commerce - Consumer Finance 0.5 0.4 0.45 104
1505: Domestic Commerce - Insurance Regulation 0.71 0.78 0.74 105
1507: Domestic Commerce - Bankruptcy 0.7 0.6 0.65 134
1520: Domestic Commerce - Corporate Management 0.74 0.59 0.66 463
1521: Domestic Commerce - Small Businesses 0.74 0.65 0.69 237
1522: Domestic Commerce - Copyrights and Patents 0.93 0.82 0.87 201
1523: Domestic Commerce - Disaster Relief 0.75 0.65 0.69 255
1524: Domestic Commerce - Tourism 0.72 0.77 0.75 148
1525: Domestic Commerce - Consumer Safety 0.72 0.72 0.72 239
1526: Domestic Commerce - Sports Regulation 0.84 0.87 0.85 630
1598: Domestic Commerce - Research and Development 0 0 0 1
1599: Domestic Commerce - Other 0.87 0.61 0.71 33
1600: Defense - General 0.69 0.67 0.68 572
1602: Defense - Alliances 0.63 0.62 0.62 358
1603: Defense - Intelligence 0.71 0.65 0.68 259
1604: Defense - Readiness 0.6 0.39 0.47 161
1605: Defense - Nuclear Arms 0.71 0.77 0.74 292
1606: Defense - Military Aid 0.66 0.61 0.63 62
1608: Defense - Personnel Issues 0.68 0.7 0.69 643
1610: Defense - Procurement 0.49 0.57 0.53 107
1611: Defense - Installations & Land 0.6 0.67 0.63 116
1612: Defense - Reserve Forces 0.76 0.73 0.74 48
1614: Defense - Hazardous Waste 0 0 0 5
1615: Defense - Civil 0.7 0.75 0.72 236
1616: Defense - Civilian Personnel 0.83 0.13 0.22 39
1617: Defense - Contractors 0.61 0.47 0.53 75
1619: Defense - Foreign Operations 0.71 0.71 0.71 518
1620: Defense - Claims against Military 0.81 0.7 0.75 198
1698: Defense - Research and Development 1 0.09 0.17 22
1699: Defense - Other 0.58 0.38 0.45 40
1700: Technology - General 0.58 0.58 0.58 177
1701: Technology - Space 0.84 0.84 0.84 80
1704: Technology - Commercial Use of Space 0.71 0.56 0.62 18
1705: Technology - Science Transfer 0.75 0.45 0.57 33
1706: Technology - Telecommunications 0.78 0.74 0.76 231
1707: Technology - Broadcast 0.69 0.56 0.62 442
1708: Technology - Weather Forecasting 0.93 0.86 0.89 44
1709: Technology - Computers 0.59 0.64 0.61 83
1798: Technology - Research and Development 0.79 0.86 0.83 408
1799: Technology - Other 0.83 0.42 0.56 24
1800: Foreign Trade - General 0.77 0.53 0.63 173
1802: Foreign Trade - Trade Agreements 0.7 0.6 0.64 183
1803: Foreign Trade - Exports 0.56 0.59 0.58 64
1804: Foreign Trade - Private Investments 0.45 0.64 0.53 124
1806: Foreign Trade - Competitiveness 0.37 0.19 0.25 53
1807: Foreign Trade - Tariff & Imports 0.75 0.71 0.73 178
1808: Foreign Trade - Exchange Rates 0.62 0.4 0.49 52
1899: Foreign Trade - Other 1 0.14 0.25 7
1900: International Affairs - General 0.57 0.51 0.54 396
1901: International Affairs - Foreign Aid 0.6 0.58 0.59 106
1902: International Affairs - Resources Exploitation 0.67 0.38 0.48 48
1905: International Affairs - Developing Countries 0.55 0.49 0.52 47
1906: International Affairs - International Finance 0.53 0.42 0.47 119
1910: International Affairs - Western Europe 0.65 0.7 0.68 578
1921: International Affairs - Specific Country 0.84 0.81 0.82 1679
1925: International Affairs - Human Rights 0.62 0.53 0.57 190
1926: International Affairs - Organizations 0.72 0.67 0.69 259
1927: International Affairs - Terrorism 0.65 0.59 0.62 162
1929: International Affairs - Diplomats 0.59 0.62 0.6 248
1999: International Affairs - Other 0.77 0.43 0.56 23
2000: Government Operations - General 0.76 0.65 0.7 950
2001: Government Operations - Intergovernmental Relations 0.66 0.71 0.68 1340
2002: Government Operations - Bureaucracy 0.61 0.54 0.57 564
2003: Government Operations - Postal Service 0.86 0.82 0.84 179
2004: Government Operations - Employees 0.68 0.57 0.62 609
2005: Government Operations - Appointments 0.82 0.72 0.77 210
2006: Government Operations - Currency 0.63 0.62 0.63 171
2007: Government Operations - Procurement & Contractors 0.72 0.6 0.66 440
2008: Government Operations - Property Management 0.63 0.56 0.6 474
2009: Government Operations - Tax Administration 0.69 0.64 0.67 208
2010: Government Operations - Scandals 0.71 0.51 0.59 300
2011: Government Operations - Branch Relations 0.59 0.53 0.56 949
2012: Government Operations - Political Campaigns 0.76 0.77 0.77 1040
2013: Government Operations - Census & Statistics 0.92 0.82 0.87 56
2014: Government Operations - Capital City 0.81 0.8 0.81 357
2015: Government Operations - Claims against the government 0.63 0.76 0.69 881
2030: Government Operations - National Holidays 0.69 0.55 0.61 111
2099: Government Operations - Other 0.44 0.36 0.4 110
2100: Public Lands - General 0.65 0.32 0.43 122
2101: Public Lands - National Parks 0.8 0.78 0.79 654
2102: Public Lands - Indigenous Affairs 0.9 0.85 0.88 240
2103: Public Lands - Public Lands 0.74 0.65 0.69 947
2104: Public Lands - Water Resources 0.75 0.85 0.8 652
2105: Public Lands - Dependencies & Territories 0 0 0 2
2199: Public Lands - Other 0.88 0.74 0.8 19
2300: Culture 0.8 0.81 0.8 818
999: No Policy Content 0.96 0.98 0.97 100986

Inference platform

This model is used by the CAP Babel Machine, an open-source and free natural language processing tool, designed to simplify and speed up projects for comparative research.

Cooperation

Model performance can be significantly improved by extending our training sets. We appreciate every submission of CAP-coded corpora (of any domain and language) at poltextlab{at}poltextlab{dot}com or by using the CAP Babel Machine.

Debugging and issues

This architecture uses the sentencepiece tokenizer. In order to run the model before transformers==4.27 you need to install it manually.

Downloads last month
1,716
Safetensors
Model size
0.6B params
Tensor type
F32
·
Inference Providers NEW
Text Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for poltextlab/xlm-roberta-large-pooled-cap-minor-v4

Base model

FacebookAI/xlm-roberta-large
Finetuned
(870)
this model

Evaluation results