A Knowledge-Grounded Neural Conversation Model
This addresses the limitation of neural models in task-oriented conversational applications by enabling more contentful responses without slot filling, though it is an incremental advancement over existing Seq2Seq methods.
The paper tackles the problem of neural conversation models lacking factual grounding by introducing a knowledge-grounded model that conditions responses on both conversation history and external facts, resulting in significant improvements over a Seq2Seq baseline and outputs judged as more informative by human evaluators.
Neural network models are capable of generating extremely natural sounding conversational interactions. Nevertheless, these models have yet to demonstrate that they can incorporate content in the form of factual information or entity-grounded opinion that would enable them to serve in more task-oriented conversational applications. This paper presents a novel, fully data-driven, and knowledge-grounded neural conversation model aimed at producing more contentful responses without slot filling. We generalize the widely-used Seq2Seq approach by conditioning responses on both conversation history and external "facts", allowing the model to be versatile and applicable in an open-domain setting. Our approach yields significant improvements over a competitive Seq2Seq baseline. Human judges found that our outputs are significantly more informative.