Joint Embedding of Words and Labels for Text Classification.
Guoyin WangChunyuan LiWenlin WangYizhe ZhangDinghan ShenXinyuan ZhangRicardo HenaoLawrence CarinPublished in: CoRR (2018)
Keyphrases
- text classification
- unlabeled documents
- n gram
- text documents
- training documents
- multi label
- distributional clustering
- text categorization
- bag of words
- training corpus
- text representation
- word segmentation
- text mining
- vector space
- multi label classification
- document classification
- naive bayes
- text classifiers
- information theoretic
- text data
- machine learning
- automatic text classification
- semantic features
- labeled data
- unlabeled data
- feature selection
- pairwise
- sentiment analysis
- language modeling
- knn
- graph cuts
- training set
- training data
- class labels
- low level features
- document clustering
- watermarking algorithm
- data hiding
- semi supervised learning
- knowledge discovery
- word sense disambiguation
- semantic classes
- natural language
- keywords