Evolving Domain Adaptation of Pretrained Language Models for Text Classification.
Yun-Shiuan ChuangYi WuDhruv GuptaRheeya UppaalAnanya KumarLuhang SunMakesh Narsimhan SreedharSijia YangTimothy T. RogersJunjie HuPublished in: CoRR (2023)
Keyphrases
- domain adaptation
- language model
- text classification
- labeled data
- sentiment classification
- language modeling
- n gram
- document classification
- co training
- transfer learning
- unlabeled data
- statistical language modeling
- sentiment analysis
- document level
- semi supervised learning
- probabilistic model
- text categorization
- text mining
- bag of words
- information retrieval
- machine learning
- feature selection
- target domain
- document retrieval
- test collection
- retrieval model
- text data
- cross domain
- query expansion
- naive bayes
- k nearest neighbor
- text documents
- knn
- semi supervised
- text classifiers
- multiple sources
- unsupervised learning
- opinion mining
- word segmentation
- data model
- prior knowledge