Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data.
Wei ZhaoLiang WangKewei ShenRuoyu JiaJingming LiuPublished in: CoRR (2019)
Keyphrases
- error correction
- unlabeled data
- labeled data
- number of labeled examples
- labeled training data
- semi supervised learning
- supervised learning
- training set
- semi supervised
- labeled data for training
- training examples
- active learning
- co training
- labeled examples
- training data
- text classification
- error detection
- semi supervised classification
- labeled and unlabeled data
- training and test data
- text categorization
- unlabeled training data
- learning algorithm
- labeled instances
- error correcting
- data points
- supervised methods
- decision trees
- class labels
- domain adaptation
- training process
- supervised learning algorithms
- training samples
- multi view
- ensemble learning
- learning problems
- transfer learning
- pairwise
- positive examples
- watermarking scheme
- test data
- labeling effort
- data analysis
- similarity measure