Italian Legal Named Entity Recognition (NER)

ELECTRA-based model trained to extract entities of interest from Italian civil judgments issued by the Corte Suprema di Cassazione.

Dataset

The model has been fine-tuned on 9000 judgments from 2016 to 2021 (1500 per year), labeled with a combination of rule-based and manual approaches. It can be used to extract the following named entities from the text.

Tag Italian name English name
RIC ricorso appeal
RCR ricorrente petitioner
CTR controricorrente respondent
AVV avvocato lawyer
CNS consigliere counselor
PMI pubblico ministero prosecutor
DOM domicilio domicile
CDA corte d’appello appeal court
SNT sentenza judgment
Downloads last month
32
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using fabiod20/italian-legal-ner 1