2000 character limit reached
Alquist: The Alexa Prize Socialbot (1804.06705v1)
Published 18 Apr 2018 in cs.CL
Abstract: 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.
- Jan Pichl (9 papers)
- Petr Marek (59 papers)
- Jakub Konrád (8 papers)
- Martin Matulík (2 papers)
- Hoang Long Nguyen (8 papers)
- Jan Šedivý (11 papers)