Leverage Unlabeled Data for Abstractive Speech Summarization with Self-Supervised Learning and Back-Summarization.
Paul TardyLouis de SeynesFrançois HernandezVincent NguyenDavid JaniszekYannick EstèvePublished in: CoRR (2020)
Keyphrases
- unlabeled data
- supervised learning
- active learning
- learning algorithm
- labeled data
- semi supervised learning
- labeled and unlabeled data
- co training
- semi supervised
- domain adaptation
- supervised learning algorithms
- learning process
- text classification
- prior knowledge
- learning problems
- data points
- multi view learning
- positive examples
- machine learning
- class labels
- text categorization
- unsupervised learning
- maximum likelihood
- knowledge discovery
- labeled instances
- supervised and semi supervised
- labeled training data
- single view
- training examples