Projects made in Natural Language Processing course at the Tomorrow Research and Training Center in UFBA Professor: Marlo Souza
- This code performs the morphological analysis of the given text (string of characters) and returns a list of items, each containing: the textual form of the token, its grammatical class and inflections (gender, number, tense, etc.).
- NOUN: Gênero (Gender) e Número (Number)
- ADJ: Gênero (Gender) e Número (Number)
- VERB: Gênero (Gender), Pessoa (Person), Tempo (Tense) e Forma Verbal (VerbForm)
- PRON: Gênero (Gender) e Número (Number), Tipo (PronType)
- DET: Gênero (Gender) e Número (Number)
- This algorithm uses SentenceTransformer to measure the similarity between user input and the description of articles in the "Código de Defesa do Consumidor"
- To execute the code it is necessary to load the "dados_cdc.csv" that was attached to the code