Home

This program identifies NER (Named Entity Recognition) and is divided into 3 parts:

• LSTM (Long short-term memory) in the lstm_ner folder must place the training data in the data folder and the training in the dataset folder
• The dataset vectors were generated in the Word2vec folder
• The folder "Mineração de Texto - Artigo" were tests carried out at the Text Mining academy without using the baseline
• The "Testes - Artigos" folder were tests carried out at the Text Mining academy using the baseline