A Sequential Neural Approach on Task-Oriented Dialogue

Frank T. Tillman
Cardinal Gibbons High School, North Charleston, South Carolina

Abstract

Task-oriented dialogue focuses on conversational agents that participate in dialogues with user goals on domain-specific topics. In reference to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented agents usually explicitly model user intent and belief states. This paper examines bypassing such an explicit representation by depending on a latent neural embedding of state and learning selective attention to dialogue history together with copying to incorporate relevant prior context. We complement recent work by showing the effectiveness of simple sequence-to-sequence neural architectures with a copy mechanism. Our model outperforms more complex memory-augmented models by 7% in per response generation and is on par with the current state of the art on DSTC2, a real world task-oriented dialogue dataset.

Please click to read the paper.