Julia Kiseleva

adversarial learning (3) reward model (2) dialogue system (2) reinforcement learning (2) dialogue policy (2) adversarial training (2) dialogue generation (1) question generation (1) meeting summarization (1) task-oriented dialogue (1) feedback learning (1) neural text generation (1) inverse reinforcement learning (1) human-ai collaboration (1) conversational ai (1) task execution (1) task decomposition (1) policy learning (1) interactive agent (1) supervised learning (1)