BB25HLegalSum : a method for legal document summarization that leverages BM25 and BERT-based clustering

• Ano de defesa: 2024
• Autor(a) principal: Andrade, Leonardo Bonalume de
• Orientador(a): Becker, Karin
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Palavras-chave em Português: Sumarizador de conteúdo; Processamento de linguagem natural; Resumo automático de texto; Algoritmos
• Palavras-chave em Inglês: Text summarization; Legal documents; BERT; Multiple color highlighting; Multiple criteria highlighting
• Link de acesso: http://hdl.handle.net/10183/273151

Legal document summarization aims to provide a clear understanding of the main points and arguments in a legal document, contributing to the efficiency of the judicial system. In this work, we propose BB25HLegalSum, a method that combines BERT clusters with the BM25 algorithm to summarize legal documents and present them to users with highlighted important information. The process involves selecting unique sentences from the original document, clustering them to find sentences about a similar subject, scoring clusters and sentences to generate a summary according to three strategies, and highlighting them to the user in the original document. Legal workers positively assessed the highlighted presentation.