Damien Jose

representation learning (1) zero-shot learning (1) adversarial learning (1) off-policy evaluation (1) few-shot learning (1) domain adaptation (1) prototype learning (1) self-supervised learning (1) named entity recognition (1) policy learning (1) dense retrieval (1) importance sampling (1) learning to rank (1) combinatorial bandit (1) pre-trained language model (1) slate recommendation (1)