Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
This work addresses the problem of building fluent casual conversation systems for users, though it appears incremental as it builds on existing retrieval and generative models with a novel architectural twist.
The paper tackles the challenge of creating engaging non-goal-oriented conversational agents by introducing Tartan, a socialbot that uses a dynamic finite-state machine architecture for dialog management, which achieved competitive performance in the 2018 Alexa Prize Competition.
This paper describes the Tartan conversational agent built for the 2018 Alexa Prize Competition. Tartan is a non-goal-oriented socialbot focused around providing users with an engaging and fluent casual conversation. Tartan's key features include an emphasis on structured conversation based on flexible finite-state models and an approach focused on understanding and using conversational acts. To provide engaging conversations, Tartan blends script-like yet dynamic responses with data-based generative and retrieval models. Unique to Tartan is that our dialog manager is modeled as a dynamic Finite State Machine. To our knowledge, no other conversational agent implementation has followed this specific structure.