Tam Minh Nguyen

sequence tagging (3) semi-supervised learning (3) toxic span detection (3) ensemble method (2) language model (2) ensemble learning (2) linear attention (1) language model fine-tuning (1) multi-head attention (1) word embedding (1) transformer language model (1) embedding method (1) long sequence (1) transformer model (1) neural transformer (1) transformer architecture (1) mixture of gaussian key (1) transfer learning (1) embedding learning (1) language modeling (1)