SlugBot: Developing a Computational Model andFramework of a Novel Dialogue Genre
This work addresses the problem of creating more advanced conversational AI for competition settings, but it is incremental as it builds on existing dialogue system frameworks without demonstrating broad SOTA impact.
The paper tackles the challenge of developing computational dialogue models for the Amazon Alexa Prize, which requires capabilities beyond traditional task-oriented or search-oriented dialogue systems, by introducing the Discourse Relation Dialogue Model and implementing it in SlugBot, resulting in the creation of a novel ontological resource called UniSlug.
One of the most interesting aspects of the Amazon Alexa Prize competition is that the framing of the competition requires the development of new computational models of dialogue and its structure. Traditional computational models of dialogue are of two types: (1) task-oriented dialogue, supported by AI planning models,or simplified planning models consisting of frames with slots to be filled; or (2)search-oriented dialogue where every user turn is treated as a search query that may elaborate and extend current search results. Alexa Prize dialogue systems such as SlugBot must support conversational capabilities that go beyond what these traditional models can do. Moreover, while traditional dialogue systems rely on theoretical computational models, there are no existing computational theories that circumscribe the expected system and user behaviors in the intended conversational genre of the Alexa Prize Bots. This paper describes how UCSC's SlugBot team has combined the development of a novel computational theoretical model, Discourse Relation Dialogue Model, with its implementation in a modular system in order to test and refine it. We highlight how our novel dialogue model has led us to create a novel ontological resource, UniSlug, and how the structure of UniSlug determine show we curate and structure content so that our dialogue manager implements and tests our novel computational dialogue model.