metadata

license: apache-2.0
language:
  - ca
  - da
  - de
  - en
  - es
  - fr
  - nl
  - el
  - is
  - it
  - 'no'
  - pt
  - sv
pipeline_tag: text-classification

Occupational CANINE: HISCO Classification Model

Overview

OccCANINE is a version of CANINE which has been finetuned to automatically convert occupational descriptions into standardized HISCO codes using a fine-tuned CANINE model. This tool facilitates historical occupational data analysis with over 90% accuracy across 13 languages.

Key Features

High Accuracy: Over 90% accuracy, recall, and precision.
Multilingual Support: Trained on 14 million description-HISCO code pairs across 13 languages.
Efficiency: Rapidly processes descriptions into HISCO codes.

Usage

Suitable for researchers in economics and economic history and related disciplines, this model offers a streamlined solution for occupational data classification.

Getting Started

...

Contribution and Support

Developed at the University of Southern Denmark by Christian Møller Dahl [email protected] and Christian Vedel Sørensen [email protected] with contributions from various sources.

Acknowledgments

Thanks to all contributors and dataset providers.