Asset-Level Location Extraction from Corporate Sustainability PDF Reports
Abstract
This repository contains a Python script (reports_NER_for_pdf.py) that extracts location entities from PDF files and classifies them into asset-related locations and other locations. The script uses spaCy NER, dependency parsing, optional fuzzy matching with RapidFuzz, and optional BERT-based sentence classification (not yet implemented). All runtime settings are read from a configuration file (cfg.yml).
Fields of Study & Subjects
Topic Modeling
Handwritten Text Recognition Techniques
Advanced Text Analysis Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 10 February 2026
- Language
- EN