End-to-End Task-oriented Dialogue System Using Knowledge Filter and Attention Memory Pointer

The end-to-end neural model provides a more robust solution to generate responses than the traditional pipeline method in the task-oriented dialogue system. However, it is challenging to incorporate the proper knowledge into the generated response, especially when there are substantially related knowledge tuples. This paper proposes a knowledge filter and an attention memory pointer to improve the task-oriented dialogue model. Specifically, the model uses the knowledge filter to obtain the knowledge tuples most relevant to the keywords of dialog context and builds the knowledge vector. Besides, the task-oriented dialogue model usually needs to copy objects from the correct knowledge tuples to form the question's answer. We define an attention memory pointer to help the model choose the correct knowledge tuples. Finally, we conduct experiments on the In-Car Assistant dataset. The experimental results show that our model can generate more accurate responses than baseline models in automatic and human evaluations.