Published in


DREAM Team on Alexa Prize Socialbot Challenge 3

This year the Alexa Prize Committee reviewed 375 applications and selected 10 finalists. These lucky ones are the DREAM Team, which features employees of the Neural Networks and Deep Learning Lab from Moscow Institute Physics and Technology. In this article I would like to describe the main challenges that our team has to overcome in order to develop a successful SocialBot.

From left to right: Idris Yusupov, Dilyara Baymurzina, team leader Yuri Kuratov, Denis Kuznetsov, Dmitry Karpov, Le Anh, adviser Mikhail Burtsev.

For the last three years Amazon has been testing the capabilities of the voice platform known as Alexa. The Alexa Prize Socialbot Grand Challenge is a competition for student teams dedicated to the development of conversational intelligence. This year Amazon received more than 375 applications from 22 countries and selected the top 10 teams according to the following criteria:

  • Potential scientific contribution in the field.
  • Technical value of the proposed approach.
  • Novelty of the idea.
  • Ability of the team to fulfill the submitted plan.

The Alexa Prize Socialbot Grand Challenge is a part of Amazon’s mission to make the voice assistant smarter, talkative so it can become useful and exciting for users. But Amazon is not the only company in this business: Google, Apple, and Samsung are also working on their assistants.

In the contest, each team competing for the Alexa Prize had an access to the Amazon’s automatic speech recognition service to get a textual interpretation of what users say, and their text-to-speech technology to provide a response. Our main challenge is to develop a social bot that will allow Alexa to conduct a conscious conversation on a wide range of topics.

In order to activate Alexa,it is necessary to vocalize the activation phrase “Alexa”. Alexa allows you to make to-do lists, record voice messages, warn you about bad weather, or play music that suits your mood. However, all these inquiries can quickly lead to a conversation about plans for the weekend. And our mission is to ensure that Alexa can address all these inquiries. In order to do so, Alexa needs to know the user preferences and combine several conversational skills. Sounds easy, right? In fact, this task is not trivial at all.

“You can think of DREAM Socialbot as an interactive and conversational gateway that stands between the user and a ton of online content,” says Yuri Kuratov, the leader of the DREAM Team. “However, the bot should use the two-way strategy focused on the user needs and the available content.

The Socialbot has to be sensitive to the users requests. Does the user feel positive about what Socialbot said? Or does the user still have negative emotions, and Socialbot should change the topic? And who is user? And what topics are interesting to him or her?

In the contest, the team deals with:

  • Infrastructure tasks: To work, the bot has to be deployed and tested somewhere, and it is also necessary to load and run programs and models.
  • Research tasks are the most creative part of the whole process: It is necessary to come up with new models that will be integrated into the dialogue with the user. The full cycle ranges from finding a problem to formulating a research problem, collecting data, or searching for existing ones, creating a baseline model or improving existing models, and comparing them by metrics.
  • Business tasks include the work directed to interest the user during a conversation.
  • Data collection tasks — parsing news sites, more interesting and popular news, movies, ratings, and reviews on them.
Idris Yusupov and Denis Kuznetsov.

DREAM Socialbot unites and personalizes approaches based on neural networks and rules. To implement this model, we use DeepPavlov Agent, which is designed for a combination of skills and has a memory in which you can store data about the user. For achieving this goal our team applies advanced technologies in the field of conversational AI.

DREAM Socialbot combines and personalizes conversational skills based on data-driven and rule-based approaches. To implement this model, we use DeepPavlov, which is designed to combine different conversational skills. While developing we face the following challenges. The DREAM Socialbot should not cause disappointment, say stupid things, nonsense, or insult the user.

The competition helps to introduce a new generation of computer scientists and engineers to conversational AI. Besides, the Socialbot solutions of last years have served as inspiration for developing the dialogue elements that Amazon has already implemented into Alexa.

In this article, we presented a short introduction of research and engineering challenges of Socialbots development. And now the question to you: “What topics would you like to talk to Alexa about? Politics? The fashion industry? Maybe about cooking tips? Kitchen blogs?”

Follow our news on the official website and on Twitter.

After all, the most interesting part are waiting us ahead!




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

Recommended from Medium

Customer Engagement Chatbot In Banking

Survey results: What does the future of chatbots look like?

Design Good, Week 2: Keeping Up With AI

News — At The Edge — 9/23

What is Voice Recognition Technology and Its Benefits

Intelligent TB Prevention: How AI is making the difference in the Philippines

Perils Of Artificial Intelligence

Ready to start an AI business? Here’s a checklist from Zindi’s founder

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

BERT Extractive Summarizer vs Word2Vec Extractive Summarizer: Which one is better and faster?

Evaluating your text generation results? Simple as that!

Two minutes NLP — Four different approaches to Text Summarization

Mental Health Support Chatbot [NLP]