ulysses-camara/ulysses-segmenter
Pretrained segmenter models for Portuguese legislative text.
This tool helps legal professionals and researchers automatically break down lengthy Brazilian legislative documents into logical, easy-to-read segments. You input a complete legislative text, and it outputs a list of individual articles, paragraphs, or clauses. This is ideal for legal analysts, parliamentary researchers, or anyone needing to dissect complex legal documents.
No commits in the last 6 months.
Use this if you regularly process large volumes of Brazilian legislative text and need to automatically identify and extract distinct legal segments like articles or sections for easier analysis or database entry.
Not ideal if you're working with non-Brazilian legislative documents or other types of text, as its pre-trained models are highly specialized for Portuguese legislative language.
Stars
13
Forks
4
Language
Python
License
MIT
Category
Last pushed
Oct 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ulysses-camara/ulysses-segmenter"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thalesbertaglia/enelvo
A flexible normalizer for user-generated content
meedan/alegre
A text and media analysis service for Meedan Check, a collaborative media annotation platform
alan-barzilay/NLPortugues
NLPortuguês - Aprenda PLN em português! Esse repositório contem os materiais e exercícios do...
elenderg/PAL-1000
Ambiente de Desenvolvimento Integrado (ADI) contando com um explorador de arquivos, editor de...
ajdavidl/Portuguese-NLP
List of resources and tools developed with focus on Portuguese.