Published in


DREAM MIPT team selected for Alexa Prize Socialbot Grand Challenge 4 by Amazon

On Nov. 3, Amazon published the selection results for the Alexa Prize Socialbot Grand Challenge 4. The Alexa Prize committee selected nine finalists, including a student team from the MIPT’s Neural Networks and Deep Learning Lab also known as (also known as

The MIPT team is called DREAM. The students are participating for the second year in a row under the guidance of Mikhail Burtsev, head of lab. The team consists of MIPT PhD students also involved in the DeepPavlov project at the Neural Networks and Deep Learning Lab: Denis Kuznetsov, Dmitry Evseev, Anton Peganov, Alsu Sagirova, Dmitry Karpov, and Dilyara Baimurzina, the team leader.

To learn more about the DREAM socialbot architecture created for the previous competition, check out the technical report of the DREAM team from the Alexa Prize 2019 competition. After the Alexa Prize Socialbot Grand Challenge 3, the DeepPavlov team has transformed the original bot and released the first version of their artificial intelligence-driven ​​assistant — DREAM AI Assistant Demo. This bot is available on the demo website and in the Telegram messenger, in English for now. DREAM AI Assistant Demo blends together almost 40 different chit-chat and task-oriented skills to engage in open domain conversations. It relies on a selection of modern NLP models and components including 14 annotators, 4 post-annotators, and knowledge graph integration. If you have ideas and suggestions for improving the system, we welcome your feedback.

“This year we have a lot of work ahead of us,” says MIPT PhD student and DREAM’s leader Dilyara Baimurzina. “Over the past year, our original team and me have been preparing the engineering infrastructure, as well as the interaction with Amazon services. We have been learning how to test the bot and, most importantly, work in a team. So now we have everything to get right down to implementing our ideas — and get into the finals, of course!”

The Alexa Prize Socialbot Grand Challenge is a competition for undergraduate, graduate, and doctoral students. It was first launched in 2016. The challenge is dedicated to the advancement of conversational artificial intelligence technologies. Teams have to develop a social bot that can communicate fluently with people about news and popular topics such as entertainment, sports, politics, technology, and fashion through Alexa-enabled devices. The ultimate goal is to score 4 out of 5 points and engage the judges in dialogues that last more than 20 minutes in the final round. Bot prototyping will begin in November, and the winner will be announced in August 2021.

The competition is being held for the fourth year, and this time there are nine teams participating, including the past winners of Alexa Prize Socialbot Grand Challenge 3 from Emory University, Stanford, and Czech Technical University. Each team will receive a $250,000 research grant, access to cloud computing in Amazon Web Services, and support from Alexa developers.




An open-source library for deep learning end-to-end dialog systems and chatbots

Recommended from Medium

How important is it to have live agent hand-off for a customer service chat bot

Computer Vision: The pathway to a personalized CRM experience

AI for EV Charging: How Ampcontrol Built A Brain To Manage Smart Charging

electric vehicle brain by using AI

5 Ways Artificial Intelligence Is Making a Difference in the E-commerce Industry

Why Chatbots are Buzzing in The Insurance Sector

Chatbot customer conversation

Start from not knowing

Rebooting generics to fight cancer with Laura Kleiman, Pradeep Mangalath and Catherine Del Vecchio…

AI in Games

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Darya Moroz

Darya Moroz

Community manager at DeepPavlov.

More from Medium

Case for Standardisation in Radiology Second Opinion

This stem picture depicts how nature sequences its production process, this helps in us going to standardised delivery in any service sector

Identifying Text Data Overlapping Classes

Revolutionizing Oil and Natural Gas Industries with SOTA X

Sentimental Analysis Using NLP Libraries/.