FORMAS Research Center on Data ans Natural Language aims to study, analyze and evaluate semantic-based approaches. Our main research areas are based on five major pillars on semantic-based area: Methods, Ontology, Information Extraction, Interoperability and Big Data. We deeply analyze each one of these approaches focusing on obtaining high levels of semantic and pragmatic comprehension. Visite our website for more informations.
-
CSIS method interoperates Syntactic, Semantic and Pragmatic into University Vigilance models providing image captioning for operators and systems.
-
DIGGER method uses LLMs to provide a QA for CDC legal documents.
- [Dataset: .](Link Padawan 2024)
-
DptOIE method uses the Dependence Parser and Part of Speech Tagger models trained with Stanford CoreNLP.
-
PortNOIE is a new version of DPTOIE-Neural.
-
PTOIE-Flair is a pt-br OpenIE model.
- Article
-
PTOIE-Dep is an Open Information Extractor for Portuguese language that employs Dependence Parser and Part of Speech Tagger models with Stanford CoreNLP.
- Article
-
PragmaticOIE method uses a rule-based approach to extract facts in Portuguese in a first pragmatic level.
-
ImageCaptioningPT methods to generate image captioning in the Portuguese language.