Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation.
Sangwon YoonYanghoon KimKyomin JungPublished in: SemEval@ACL/IJCNLP (2021)
Keyphrases
- domain adaptation
- multiple sources
- target domain
- source domain
- cross domain
- labeled data
- transfer learning
- semi supervised
- semi supervised learning
- test data
- source and target domains
- sentiment classification
- covariate shift
- domain specific
- training samples
- unlabeled data
- word sense disambiguation
- training data
- multi view
- text classification
- machine learning
- similarity measure
- feature extraction
- face recognition
- learning algorithm