What we need to learn if we want to do and not just talk

Abstract

In task-oriented dialog, agents need to generate both fluent natural language responses and correct external actions like database queries and updates. We show that methods that achieve state of the art performance on synthetic datasets, perform poorly in real world dialog tasks. We propose a hybrid model, where nearest neighbor is used to generate fluent responses and Sequence-to-Sequence (Seq2Seq) type models ensure dialogue coherency and generate accurate external actions. The hybrid model on an internal customer support dataset achieves a 78% relative improvement in fluency, and a 200% improvement in external call accuracy.