PNRR project: “Giustizia Agile” Digitalization of Court’s law cases.
Participated in building an intelligent database and searc engine for legal texts (civil law court cases)
Tasks included:
- Design and supervision of semi-automatic data annotation pipeline
- Data conversion, cleaning, preprocessing and analysis
- Machine learning models Training (sci-kit-learn)
- NLP tools implementation (spacy)
- Transformers Fine-Tuning (NER, Document classification)