GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions
This provides the Italian legal community with a tailored tool for de-identification to balance privacy and data protection, though it is incremental as it adapts an existing method to a specific domain.
The paper tackled the problem of anonymizing personal data in Italian legal documents by developing GiusBERTo, a BERT-based model specialized for this task, achieving 97% token-level accuracy on a test set.
Recent advances in Natural Language Processing have demonstrated the effectiveness of pretrained language models like BERT for a variety of downstream tasks. We present GiusBERTo, the first BERT-based model specialized for anonymizing personal data in Italian legal documents. GiusBERTo is trained on a large dataset of Court of Auditors decisions to recognize entities to anonymize, including names, dates, locations, while retaining contextual relevance. We evaluate GiusBERTo on a held-out test set and achieve 97% token-level accuracy. GiusBERTo provides the Italian legal community with an accurate and tailored BERT model for de-identification, balancing privacy and data protection.