Combining Feature-Based and Instance-Based Transfer Learning Approaches for Cross-Domain Hedge Detection with Multiple Sources.
Huiwei ZhouHuan YangLong ChenZhenwei LiuJianjun MaDegen HuangPublished in: SMP (2015)
Keyphrases
- cross domain
- transfer learning
- multiple sources
- target domain
- domain adaptation
- cross domain text classification
- knowledge transfer
- source domain
- learning tasks
- machine learning algorithms
- cross domain learning
- sentiment classification
- text categorization
- labeled data
- text classification
- machine learning
- active learning
- multi task
- data sets
- semi supervised learning
- collaborative filtering
- reinforcement learning
- unlabeled data
- k nearest neighbor
- semi supervised
- knn
- data sources
- feature selection
- data mining