Joint Embedding of Words and Labels for Text Classification.
Guoyin WangChunyuan LiWenlin WangYizhe ZhangDinghan ShenXinyuan ZhangRicardo HenaoLawrence CarinPublished in: ACL (1) (2018)
Keyphrases
- text classification
- unlabeled documents
- n gram
- multi label
- text documents
- training documents
- distributional clustering
- text categorization
- training corpus
- vector space
- text mining
- bag of words
- machine learning
- feature selection
- multi label classification
- naive bayes
- word segmentation
- text data
- text representation
- information theoretic
- labeled data
- class labels
- pairwise
- text classifiers
- sentiment analysis
- sentiment classification
- document classification
- unlabeled data
- training data
- keywords
- knn
- word sense disambiguation
- part of speech
- semantic features
- probabilistic model
- data cleaning
- multiword
- automatic text classification
- term frequency
- graph cuts
- training examples
- feature extraction
- semi supervised learning
- data mining