BERTifying Sinhala - A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification.
Vinura DhananjayaPiyumal DemotteSurangika RanathungaSanath JayasenaPublished in: CoRR (2022)
Keyphrases
- comprehensive analysis
- language model
- text classification
- pre trained
- language modeling
- n gram
- training data
- information retrieval
- statistical language modeling
- probabilistic model
- language modelling
- bag of words
- query expansion
- training examples
- feature selection
- test collection
- retrieval model
- machine learning
- statistical language models
- naive bayes
- text documents
- document retrieval
- language models for information retrieval
- text categorization
- labeled data
- text mining
- context sensitive
- speech recognition
- smoothing methods
- multi label
- relevance model
- translation model
- unlabeled data
- multi modal
- bayesian networks