Understanding the effects of language-specific class imbalance in multilingual fine-tuning.
Vincent JungLonneke van der PlasPublished in: CoRR (2024)
Keyphrases
- language specific
- fine tuning
- class imbalance
- language independent
- natural language
- machine translation
- cross lingual
- n gram
- class distribution
- cost sensitive
- active learning
- concept drift
- specific features
- labor intensive
- high dimensionality
- feature selection
- out of vocabulary
- pattern recognition
- machine learning
- text classification
- language model
- natural language processing