KIDER: Knowledge-Infused Document Embedding Representation for Text Categorization.
Yu-Ting ChenZheng-Wen LinYung-Chun ChangWen-Lian HsuPublished in: IEA/AIE (2020)
Keyphrases
- text categorization
- document classification
- text documents
- external knowledge
- term frequency
- text classifiers
- text representation
- tf idf
- document categorization
- text classification
- training documents
- text collections
- automatic text categorization
- knn
- automatic categorization
- feature selection
- k nearest neighbor
- multi label
- information gain
- semi supervised learning
- document frequency
- naive bayes
- document clustering
- term weighting
- term selection
- text mining
- reuters corpus
- neural network
- feature selections
- classify documents
- document collections
- unlabeled data
- nearest neighbor
- labeled data
- semi supervised
- data analysis
- keywords
- machine learning
- data sets
- feature selection for text categorization