A team of postgraduate students from the University of Glasgow have stepped up work on next-generation conversational AI.
The computing science students are one of ten teams chosen by tech giant Amazon from more than 125 entries across 15 countries to compete in the first Alexa Prize Taskbot Challenge.
Working as part of the Glasgow Representation and Information Learning Lab (GRILL), the team is starting work on an AI assistant to guide Amazon Alexa users “through complex real-world tasks,” focusing initially on cooking and home improvement.
The GRILL team consists of School of Computing Science graduate students Sophie Fischer, Carlos Gemmell, Iain Mackie, Paul Owoicho, and Federico Rossetto.
The team’s leader, Carlos Gemmell, said: “We’re thrilled that our entry was successful, and we’re excited to begin work on the Alexa Taskbot project.
“Over the next 12 months, we’ll develop novel multimodal deep learning algorithms grounded in tasks that people do in the real world. It will be capable of understanding what users require when performing a task and how to guide them through it by reasoning over past interactions, a structured representation of the task, and curated documents.
“The project aims to develop new conversational question answering technology specialised for complex tasks using state-of-the-art neural deep learning models. Having access to Alexa users around the world will allow us to receive real-time feedback and help us to make it an invaluable task assistant.”
A research grant of $250,000 (£176,500) will be provided to the team to aid them over the next 12 months. They will also receive four Amazon Alexa devices as well as free access to Amazon Web Services, and support from members of the Amazon Alexa team.
Commenting on the achievement, Dr Jeff Dalton, GRILL lab head and lecturer in the School of Computing Science, said: “Conversational AI assistants like Alexa have come a long way in recent years, but ambitious projects like this are vital to significantly advance their abilities.
“The team aims to help agents understand what users are doing and how they’re doing it by grounding conversations in the world.
“Ultimately, we hope that GRILL will be able to help people solve complex tasks in the kitchen and beyond. To adapt a recipe to the unexpected dietary preferences of a dinner party guest, explain the reason for adding cornstarch to scrambled eggs and diagnose failed sourdough bread.
“Although this is an ambitious vision beyond current capability, our team will make key advances towards this goal with multi-modal and visually grounded conversation capability.”
- DIGIT Leader Summit 2021 | Leaders must step up to drive change
- Online shopping fatigue? Half of Scots consumers prefer the high street
- Skyscanner co-founder pledges £1.5m support for home security startup, Boundary
Amazon’s Alexa Prize, an annual university competition dedicated to accelerating the field of conversational AI, recognises students worldwide who are “changing the way we interact with technology”.
This year’s taskbot challenge is the first to incorporate multimodal (voice and vision) customer experiences.