Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP.
Lukas GalkeAnsgar ScherpPublished in: ACL (1) (2022)
Keyphrases
- bag of words
- text classification
- text documents
- text data
- text mining
- world knowledge
- textual features
- text representation
- text classifiers
- visual words
- text categorization
- n gram
- document representation
- neural network
- feature selection
- naive bayes
- information retrieval
- word frequency
- structured data
- image representation
- term frequency
- web graph
- multi label
- action recognition
- information extraction
- image classification
- labeled data
- text classification tasks
- text collections
- sentiment classification
- data mining
- sentiment analysis
- k nearest neighbor
- tf idf
- text retrieval
- machine learning
- bag of words models
- semantic features
- document clustering
- semantic information
- data analysis
- object recognition
- keywords
- feature engineering