Athena: Constructing Dialogues Dynamically with Discourse Constraints
This work aims to improve the flexibility and coherence of spoken dialogue systems for general users, which is an incremental improvement to existing dialogue management.
This paper introduces Athena, a dialogue system for spoken conversations on popular topics and current events. It uses a topic-agnostic approach to dynamically configure dialogues based on entity and topic coherence, allowing it to retrieve responses from various dynamic sources.
This report describes Athena, a dialogue system for spoken conversation on popular topics and current events. We develop a flexible topic-agnostic approach to dialogue management that dynamically configures dialogue based on general principles of entity and topic coherence. Athena's dialogue manager uses a contract-based method where discourse constraints are dispatched to clusters of response generators. This allows Athena to procure responses from dynamic sources, such as knowledge graph traversals and feature-based on-the-fly response retrieval methods. After describing the dialogue system architecture, we perform an analysis of conversations that Athena participated in during the 2019 Alexa Prize Competition. We conclude with a report on several user studies we carried out to better understand how individual user characteristics affect system ratings.