Multi-action dialog policy (MADP), which generates multiple atomic actions per turn, has been widely applied in task-oriented systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action samples. Due data limitations, they generalize poorly toward unseen flows. While reinforcement learning-based methods are ...

Channel feedback for multi-user (MU)-multiple-input multiple-output (MIMO) has been widely studied and some results have been got with random vector quantization scheme. However, while the low rate fixed codebook feedbacks are adopted, the performance of zero forcing (ZF) MU-MIMO will decrease as the unpredictable interuser interference is introduced because of quantized channel state informati...

Improving physical activity patterns is an important focus in the treatment of chronic illnesses. We describe a system to monitor activity and provide feedback to help patients reach a healthy daily pattern. The system has shown positive effects in trials on patient groups including COPD and obese patients. We describe the design and implementation of a new feedback generation module which impr...

This paper follows on from a group of internationally published papers in the area of investigating anthropomorphic user interface feedback. In this paper an experiment is described which aims to examine the effectiveness and user approval issues of anthropomorphic versus non-anthropomorphic user interface feedback. This experiment is highly relevant to the research community as Computer Scient...