Jan Cegin

large language model (5) data augmentation (3) low-resource language (3) text augmentation (3) text classification (2) synthetic data generation (2) synthetic datum (2) ensemble learning (1) model selection (1) cross-lingual transfer (1) intent classification (1) paraphrase generation (1) pre-trained language model (1) transfer learning (1) parameter-efficient fine-tuning (1) knowledge distillation (1) sample selection (1) noise regularization (1) model robustness (1) domain generalization (1)