Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers.
Frederico Dias SouzaJoão Baptista de Oliveira e Souza FilhoPublished in: CoRR (2022)
Keyphrases
- bag of words
- text classification
- brazilian portuguese
- visual words
- text mining
- text categorization
- document representation
- text documents
- n gram
- naive bayes
- machine learning
- sentiment analysis
- machine translation
- image classification
- knn
- feature selection
- labeled data
- term frequency
- sentiment classification
- text data
- text classification tasks
- semantic features
- bag of words models
- multi label
- vector space
- spatial pyramid matching
- feature engineering
- portuguese language
- neural network
- image representation
- information extraction
- knowledge discovery
- image retrieval
- text representation
- pairwise
- fisher kernel
- computer vision
- artificial intelligence