Enhancing LSTM-based Word Segmentation Using Unlabeled Data.
Bo ZhengWanxiang CheJiang GuoTing LiuPublished in: CCL (2017)
Keyphrases
- word segmentation
- unlabeled data
- text classification
- labeled data
- semi supervised learning
- semi supervised
- co training
- n gram
- active learning
- training data
- text categorization
- labeled and unlabeled data
- supervised learning
- language independent
- machine learning
- training set
- text mining
- text documents
- class labels
- cross lingual
- language modeling
- learning algorithm
- naive bayes
- feature selection
- domain adaptation
- data points
- pairwise
- transfer learning
- prior knowledge
- probabilistic model
- pattern recognition
- knn
- data sets
- bayesian networks
- document analysis
- multimedia