Variational Reward Estimator Bottleneck: Learning Robust Reward Estimator for Multi-Domain Task-Oriented Dialog

no code implementations • 31 May 2020 • Jeiyoon Park, Chanhee Lee, Kuekyeng Kim, Heuiseok Lim

Despite its notable success in adversarial learning approaches to multi-domain task-oriented dialog system, training the dialog policy via adversarial inverse reinforcement learning often fails to balance the performance of the policy generator and reward estimator.

reinforcement-learning Reinforcement Learning (RL)

GREG: A Global Level Relation Extraction with Knowledge Graph Embedding

no code implementations • Appl. Sci. 2020 2020 • Kuekyeng Kim, Yuna Hur, Gyeongmin Kim, Heuiseok Lim

Currently, most relation extraction modules are more focused on the extraction of local mention-level relations—usually from short volumes of text.

Knowledge Graph Embedding Knowledge Graph Embeddings +3