Alquist: The Alexa Prize Socialbot
This work addresses the problem of building engaging dialogue systems for voice assistants like Amazon Echo, but it appears incremental as it builds on existing methods without introducing a new paradigm.
The authors tackled the challenge of creating an open-domain socialbot for the Alexa Prize competition, resulting in a hybrid system that combines machine learning and rule-based approaches to conduct coherent conversations on popular topics, though no concrete performance numbers are provided.
This paper describes a new open domain dialogue system Alquist developed as part of the Alexa Prize competition for the Amazon Echo line of products. The Alquist dialogue system is designed to conduct a coherent and engaging conversation on popular topics. We are presenting a hybrid system combining several machine learning and rule based approaches. We discuss and describe the Alquist pipeline, data acquisition, and processing, dialogue manager, NLG, knowledge aggregation and hierarchy of sub-dialogs. We present some of the experimental results.