Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization.
Junxin LiuFangzhao WuChuhan WuYongfeng HuangXing XiePublished in: CoRR (2019)
Keyphrases
- unlabeled data
- chinese word segmentation
- multi view learning
- semi supervised learning
- labeled data
- semi supervised
- active learning
- pos tagging
- supervised learning
- word segmentation
- text classification
- co training
- data points
- domain adaptation
- learning algorithm
- training data
- natural language understanding
- text categorization
- labeled and unlabeled data
- training set
- domain specific
- training examples
- part of speech
- machine learning
- gaussian process
- class labels
- natural language
- probabilistic model
- data analysis
- transfer learning
- decision trees
- data sets
- prior knowledge