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.
@article{arxiv.2011.10683,
title = {Athena: Constructing Dialogues Dynamically with Discourse Constraints},
author = {Vrindavan Harrison and Juraj Juraska and Wen Cui and Lena Reed and Kevin K. Bowden and Jiaqi Wu and Brian Schwarzmann and Abteen Ebrahimi and Rishi Rajasekaran and Nikhil Varghese and Max Wechsler-Azen and Steve Whittaker and Jeffrey Flanigan and Marilyn Walker},
journal= {arXiv preprint arXiv:2011.10683},
year = {2020}
}