Hong Meng Yam

model compression (1) contrastive learning (1) adversarial learning (1) text classification (1) knowledge distillation (1) data augmentation (1) deep learning (1) ensemble method (1) language model (1) ensemble model (1) word embedding (1) pre-training datum (1) data composition (1) model capacity (1) transformer-based model (1) small language model (1) sample-efficient training (1) glove embedding (1)