Roymond Liao

Latest

• [Paper-NLP] ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
• [Paper-NLP] Is Word Segmentation Necessary for Deep Learning of Chinese Representations?
• Transformer Part 3 - Transformer
• Transformer Part 2 - Attention
• Transformer Part 1 - Seq2Seq
• Adversarial validation
• Lookahead Optimizer: k steps forward, 1 step back
• Faster R-CNN
• Word2Vec
• DropBlock
• XGBoost