Chen Liang

BOND. BOND: BERT-Assisted Open-Domain Name Entity Recognition with Distant Supervision

task-aware-distillation. Less is More: Task-aware Layer-wise Distillation for Language Model Compression (ICML2023)

SAGE. No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models (ICLR 2022)

super-structured-lottery-tickets. Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization (ACL 2021)

CAMERO. CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing (ACL 2022)

adfraud_detection_visualization. simplified version of adclick fraud detection with visualization build-in based on Kaggle's talkingdata challenge

token-wise-curriculum-learning. Token-wise Curriculum Learning for Neural Machine Translation