Alexa Prize SocialBot Grand Challenge 4
Congratulations to Team Alquist from the Czech Technical University.
Team Alquist from Czech Technical University won the Alexa Prize SocialBot Grand Challenge 4 competition, and was awarded the $500,000 first prize for earning the top score in the finals competition.
Although none of this year’s teams met the Grand Challenge, each finalist demonstrated impressive progress toward the goal. Alquist, the socialbot from CTU, earned first place with a 3.28 average rating, and an average finals’ competition interaction duration of 14 minutes and 14 seconds.
For the second consecutive year, Stanford University’s Chirpy Cardinal socialbot earned second-place honors and a $100,000 prize by achieving a 3.25 average rating, and an average of 13 minutes and 25 seconds of interaction duration. Proto, the socialbot from the University of Buffalo team, earned third-place honors with an average rating of 3.16, and an average of 14 minutes and 45 seconds of interaction duration.
September 9, 2020
Application period opens
October 23, 2020
Application period closes
Competing teams announced
How to apply
The Alexa Prize application is hosted on the YouNooodle platform. To begin your application you must have a YouNoodle account. Please create your account by clicking “Create Account” or login below using your existing YouNoodle.com credentials. If you have started your application a link to it will also show below.
To accommodate proposers adversely affected by the ongoing pandemic to complete their applications, we are extending the submission deadline to October 23rd. In the interest of fairness, the University teams who have already submitted proposals may also use this additional time to update their proposals if they want to. All other Alexa Prize related dates (e.g. announcement of selected proposals) will remain the same.
Czech Technical University in Prague - Alquist
Alquist 4.0: Towards social intelligence using generative models and dialogue personalization
Emory University - Emora
An approach to inference-driven dialogue management within a social chatbot
Moscow Institute of Physics and Technology - DREAM
DREAM Technical Report for the Alexa Prize 4
Polytechnic University of Madrid - Genuine2
Genuine2: An open domain chatbot based on generative models
Stanford University - Chirpy Cardinal
Neural, neural everywhere: controlled generation meets scaffolded, structured dialogue
Suny Buffalo - Proto
Proto: A neural cocktail for generating appealing conversations
University of California, Santa Cruz - Athena
Athena 2.0: Discourse and user modeling in open domain dialogue
University of Southern California - Viola
Viola: A topic agnostic generate-and-rank dialogue system
University of Texas at Dallas - CASPR
CASPR: A commonsense reasoning-based conversational socialbot
You can also download all of the papers in one .zip file.