GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions.
Giulio SaliernoRosamaria BertèLuca AttiasCarla MorroneDario PettazzoniDaniela BattistiPublished in: CoRR (2024)
Keyphrases
- language model
- personal data
- data protection
- personal information
- language modeling
- privacy preserving
- probabilistic model
- n gram
- privacy protection
- information retrieval
- service providers
- retrieval model
- third party
- test collection
- data collection
- ad hoc information retrieval
- context sensitive
- privacy concerns
- mixture model
- query expansion
- data privacy
- smoothing methods
- sensitive data
- databases
- web content
- relevance feedback