MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification.
Qianli MaZhenxi LinJiangyue YanZipeng ChenLiuhong YuPublished in: EMNLP (1) (2020)
Keyphrases
- multiscale
- recurrent neural networks
- recurrent networks
- decision trees
- support vector
- pattern recognition
- classification accuracy
- preprocessing
- support vector machine svm
- feature selection
- automatic classification
- decision rules
- class labels
- neural network
- image representation
- natural images
- pattern classification
- image processing
- model selection
- machine learning algorithms
- text classification
- image classification
- machine learning methods
- feature extraction