Maximizing SLU Performance with Minimal Training Data Using Hybrid RNN Plus Rule-based Approach.
Takeshi HommaAdriano S. ArantesMaria Teresa Gonzalez DiazMasahito TogamiPublished in: SIGDIAL Conference (2018)
Keyphrases
- training data
- recurrent neural networks
- nearest neighbor
- training set
- supervised learning
- data sets
- training instances
- databases
- decision trees
- learning algorithm
- test set
- class labels
- test data
- generalization error
- search algorithm
- reinforcement learning
- support vector machine
- multiscale
- training examples
- website
- classification models
- training dataset
- positive examples
- learned from training data