Appellate Court Modifications Extraction for Portuguese

• Published in: Artificial intelligence and law 2020-09, Vol.28 (3), p.327-360
• Main Authors: Fernandes, William Paulo Ducca, Silva, Luiz José Schirmer, Frajhof, Isabella Zalcberg, de Almeida, Guilherme da Franca Couto Fernandes, Konder, Carlos Nelson, Nasser, Rafael Barbosa, de Carvalho, Gustavo Robichez, Barbosa, Simone Diniz Junqueira, Lopes, Hélio Côrtes Vieira
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Computer Science; Conditional random fields; Information retrieval; Information Storage and Retrieval; Intellectual Property; IT Law; Judicial opinions; Legal Aspects of Computing; Machine learning; Media Law; Original Research; Philosophy of Law; State court decisions
• ISSN: 0924-8463; 1572-8382
• DOI: 10.1007/s10506-019-09256-x

Appellate Court Modifications Extraction consists of, given an Appellate Court decision, identifying the proposed modifications by the upper Court of the lower Court judge’s decision. In this work, we propose a system to extract Appellate Court Modifications for Portuguese. Information extraction for legal texts has been previously addressed using different techniques and for several languages. Our proposal differs from previous work in two ways: (1)  our corpus is composed of Brazilian Appellate Court decisions, in which we look for a set of modifications provided by the Court; and (2) to automatically extract the modifications, we use a traditional Machine Learning approach and a Deep Learning approach, both as alternative solutions and as a combined solution. We tackle the Appellate Court Modifications Extraction task, experimenting with a wide variety of methods. In order to train and evaluate the system, we have built the KauaneJunior corpus, using public data disclosed by the Appellate State Court of Rio de Janeiro jurisprudence database. Our best method, which is a Bidirectional Long Short-Term Memory network combined with Conditional Random Fields, obtained an F β = 1 score of 94.79%.