A TV Program Discovery Dialog System using recommendations

摘要: We present an end-to-end conversational system for TV program discovery that uniquely combines advanced technologies NLU, Dialog Management, Knowledge Graph Inference and Personalized Recommendations. It uses a semantically rich relational representation of dialog state knowedge graph inference queries. The recommender evidence user preferences from multiple modalities such as dialog, viewing history activity logs. is tightly integrated with the System, especially explanations recommendations. A demo on iPad will be shown.