HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification.
Wenshuo YangJiyi LiFumiyo FukumotoYanming YePublished in: EMNLP (1) (2020)
Keyphrases
- multi label
- text classification
- convolutional neural network
- text categorization
- multi label classification
- face detection
- graph cuts
- binary classification
- image classification
- text mining
- bag of words
- image annotation
- multiple labels
- multi label learning
- labeled data
- naive bayes
- class labels
- machine learning
- protein function prediction
- feature selection
- class distribution
- text classifiers
- neural network
- class imbalance
- feature vectors
- cost sensitive
- unsupervised learning
- knn
- reinforcement learning
- hierarchical text categorization