Knowledge-based end-to-end memory networks
This addresses the challenge of integrating structured or unstructured knowledge into dialog systems for improved performance in goal-oriented tasks, representing an incremental advancement.
The paper tackles the problem of incorporating a-priori knowledge into end-to-end dialog systems by proposing Knowledge-based end-to-end memory networks (KB-memN2N), which specifically handle named entities for goal-oriented tasks, and reports results on the DSTC6 challenge dataset and dialog bAbI tasks.
End-to-end dialog systems have become very popular because they hold the promise of learning directly from human to human dialog interaction. Retrieval and Generative methods have been explored in this area with mixed results. A key element that is missing so far, is the incorporation of a-priori knowledge about the task at hand. This knowledge may exist in the form of structured or unstructured information. As a first step towards this direction, we present a novel approach, Knowledge based end-to-end memory networks (KB-memN2N), which allows special handling of named entities for goal-oriented dialog tasks. We present results on two datasets, DSTC6 challenge dataset and dialog bAbI tasks.