ٺƵ

Student Team Wins Amazon Alexa Artificial Intelligence Challenge

News
Members of team Gunrock, ٺƵ undergraduate and graduate students who won Amazon’s Alexa Prize competition
Team Gunrock, ٺƵ graduate and undergraduate students celebrate their first place in Amazon’s Alexa Prize competition in Las Vegas. The team took home $500,000 for creating a software bot that could hold a coherent and engaging conversation with humans. (Zhou Yu/ٺƵ)

A team of students from the University of California, Davis, has won the global 2018 Amazon Alexa Prize and a $500,000 prize for creating a “chatbot” that can converse engagingly with humans on a range of topics such as entertainment, sports, politics, technology and fashion. 

The prize was announced today (Nov. 27) at the annual Amazon Web Services re:Invent conference in Las Vegas.

Zhou Yu, an assistant professor in the College of Engineering’s Department of Computer Science, led the team of 11 graduate and undergraduate students to victory. 

“When our team first came together, we were competing against teams that had already participated in this challenge,” Yu said. “For us, it was our first time competing. Now, we are the best in the world in social conversational systems. They really came together and made this happen.”

The team’s bot — affectionately named “Gunrock” after the university’s mascot — earned a final score of 3.1 out of 5. Gunrock was able to maintain an average of 9 minutes and 59 seconds of conversation during the competition’s final round of judging. Team Alquist from the Czech Technical University in Prague earned second place with a score of 2.6.

The competition was the culmination of nearly a year of research and development efforts by Team Gunrock. The team programmed their conversational bot using data from millions of Amazon Alexa user conversations.

Some of the distinguishing features of the bot included incorporating language disfluencies — pauses such as “hm” or “ah.” These humanlike attributes help distinguish Gunrock from traditional artificial intelligence bots.

The team also designed a robust natural language understanding model for their bot, which helped it break down dialogue into self-contained semantic units and parse through language to better determine context. They integrated structured knowledge bases such as Google Knowledge into the bot. This helped Gunrock handle a wide variety of user behaviors, including topic switching and question answering.

In addition to Yu, the team includes ٺƵ students Chun-Yen Chen, Dian Yu, Weiming Wen, Yi Mang Yang, Mingyang Zhou, Kevin Jesse, Austin Chau, Antara Bhowmick, Shreenath Iyer, Giritheja Sreenivasulu and Ashwin Bhandare.

Although they have not yet decided how to use their prize money, the team will definitely compete again next year, Yu said.

Media Resources

Andy Fell, News and Media Relations, 530-752-4533, ahfell@ucdavis.edu

Zhou Yu, Computer Science, 530-752-4494, joyu@ucdavis.edu

Primary Category

Secondary Categories

Student Life

Tags