Ulysses's repositories
ulysses-segmenter
Pretrained segmenter models for Portuguese legislative text.
ulysses-curiosity
Framework for probing tasks.
ulysses-fetcher
Fetch pretrained models for Ulysses project.
ulysses-ner-br
PT-br Legal Named Entity Recognition (NER) resources
Language:Python000
Language:PythonMIT000
ulysses-optimizer
Optimization and quantization methods for pretrained Ulysses models.
Language:PythonMIT000
Ulysses-RFCorpus
Relevance Feedback dataset for Legal Information Retrieval.
000
ulysses-senteval
Benchmark for assessing contextual-semantic sentence models in Brazilian legal domain.
Language:PythonMIT000
ulysses-tesemo
Ulysses Tesemõ corpus: Brazilian corpus for judicial, legislative, and governmental textual data, scraped from more than 150 sources.
000