Papers by Nilton Correia da Silva
VICTOR: a Dataset for Brazilian Legal Documents Classification (2020.lrec-1)
Copied to clipboard
Pedro Henrique Luz de Araujo, Teófilo Emídio de Campos, Fabricio Ataides Braz, Nilton Correia da Silva
| Challenge: | Approximately 10% of these are unstructured and requiring a lot of time to sort through. |
| Approach: | They propose to use a dataset built from Brazil's Supreme Court digitalized legal documents to improve document type classification and theme assignment tasks. |
| Outcome: | The proposed dataset is based on 45 thousand appeals and contains roughly 692 thousand documents—about 4.6 million pages. |