Antonio Mauricio, Vladia Pinheiro, Vasco Furtado et al.
A basic task for most Legal Artificial Intelligence (Legal AI) applications is Named Entity Recognition (NER). However, texts produced in the context of legal practice make references to entities that are not trivially recognized by the currently available NERs. There is a lack of categorization of legislation, jurisprudence, evidence, penalties, the roles of people in a legal process (judge, lawyer, victim, defendant, witness), types of locations (crime location, defendant's address), etc. In this sense, there is still a need for a robust golden collection, annotated with fine-grained entities of the legal domain, and which covers various documents of a legal process, such as petitions, inquiries, complaints, decisions and sentences. In this article, we describe the development of the Golden Collection of the Brazilian Judiciary (CDJUR-BR) contemplating a set of fine-grained named entities that have been annotated by experts in legal documents. The creation of CDJUR-BR followed its own methodology that aimed to attribute a character of comprehensiveness and robustness. Together with the CDJUR-BR repository we provided a NER based on the BERT model and trained with the CDJUR-BR, whose results indicated the prevalence of the CDJUR-BR.