Multi-Stage Pre-training for Low-Resource Domain Adaptation.
Rong ZhangRevanth Gangi ReddyMd. Arafat SultanVittorio CastelliAnthony FerrittoRadu FlorianEfsun Sarioglu KayiSalim RoukosAvirup SilTodd WardPublished in: CoRR (2020)
Keyphrases
- multistage
- domain adaptation
- covariate shift
- single stage
- multiple sources
- dynamic programming
- training set
- lot sizing
- labeled data
- cross domain
- semi supervised
- training process
- sentiment classification
- unlabeled data
- training data
- transfer learning
- supervised learning
- document classification
- target domain
- semi supervised learning
- manifold alignment
- test set
- optimal policy
- sufficient conditions
- information sharing
- test data
- data sets
- error rate
- text categorization
- model selection
- databases