Feature Adaptation of Pre-Trained Language Models across Languages and Domains for Text Classification.
Hai YeQingyu TanRuidan HeJuntao LiHwee Tou NgLidong BingPublished in: CoRR (2020)
Keyphrases
- language model
- text classification
- language modeling
- n gram
- pre trained
- language independent
- cross lingual
- retrieval model
- statistical language modeling
- information retrieval
- probabilistic model
- text categorization
- query expansion
- speech recognition
- bag of words
- document retrieval
- statistical language models
- context sensitive
- text mining
- test collection
- labeled data
- feature selection
- training examples
- naive bayes
- training data
- smoothing methods
- machine learning
- translation model
- image features
- relevance model
- word segmentation
- text classifiers
- multi label
- unlabeled data
- semi supervised learning