DeepPavlov @ GSoC 2022
We're eager to join the Google Summer of Code 2022!
Here you can find our Top Contribution Areas with the corresponding GSoC Proposal Ideas.
But don't feel limited by these ideas, feel free to come up with your idea!
Create an issue in our GitHub, contact us via forum or TG-chat (bilingual EN/RU).
Our mentors will be happy to talk to you and help.
You can learn more about GSoC on the Official GSoC page and especially from the information for students.
Here you can find our Top Contribution Areas with the corresponding GSoC Proposal Ideas.
But don't feel limited by these ideas, feel free to come up with your idea!
Create an issue in our GitHub, contact us via forum or TG-chat (bilingual EN/RU).
Our mentors will be happy to talk to you and help.
You can learn more about GSoC on the Official GSoC page and especially from the information for students.
TOP contribution areas
Here you can find the key areas that we found important from our daily interaction with our users.
Click on the appropriate tab to see our proposed GSoC ideas for Summer 2022:
Click on the appropriate tab to see our proposed GSoC ideas for Summer 2022:
Development of a System for Automatic Evaluation of Open-Domain Dialogues
The task is to develop a system for automatic evaluation of the quality of dialogues with an Open-domain chatbot and search for problematic dialogues. The results of the work will be embedded in the dashboard for our dialog system.
They will also become part of the spam filtering system to display dialogues with the bot on our website.
duration: 350 hours
requirements: Python, NLP, ML, DL
difficulty: medium
See full details about task in the Task Page.
They will also become part of the spam filtering system to display dialogues with the bot on our website.
duration: 350 hours
requirements: Python, NLP, ML, DL
difficulty: medium
See full details about task in the Task Page.
More Research Ideas
We provide lots of Research Ideas. See all of them stored together in our regular research Ideas tracker.
duration: 350 hours
requirements: NLP, Python, and experience with papers are a must. See the task-specific details in the descriptions.
mentors: our core research team led by Mikhail Burtsev
duration: 350/175
difficulty: medium -- all the tasks are guided by experienced supervisors, yet require either scientific background or strong passion.
See the section CALL FOR PROPOSALS - 2022 under the link below.
duration: 350 hours
requirements: NLP, Python, and experience with papers are a must. See the task-specific details in the descriptions.
mentors: our core research team led by Mikhail Burtsev
duration: 350/175
difficulty: medium -- all the tasks are guided by experienced supervisors, yet require either scientific background or strong passion.
See the section CALL FOR PROPOSALS - 2022 under the link below.
Development of Dream Builder
Dream Builder is a graphical tool for creating and configuring components of the DeepPavlov Dream AI Assistant platform. It is implemented as a web app with a React frontend and a Python backend.
The task is to embed our tool for creating scenario-driven skills (DF Designer) into Dream Builder.
duration: 350 hours
requirements: fluency in TypeScript, Python, understanding of CSS, React + redux or similar state management library + FastAPI, SQL, Machine learning basics
difficulty: medium
See full details about task in the Task Page.
The task is to embed our tool for creating scenario-driven skills (DF Designer) into Dream Builder.
duration: 350 hours
requirements: fluency in TypeScript, Python, understanding of CSS, React + redux or similar state management library + FastAPI, SQL, Machine learning basics
difficulty: medium
See full details about task in the Task Page.
Dream Socialbot Landing Improvement
Dream Socialbot was originally developed for participation in Amazon Alexa Prize Challenge, and then it was converted to an open-source platform DeepPavlov Dream for building modular dialogue systems. Dream dialogue system is available for conversations on our demo web-page. Now we are working on the development of a separate landing for Dream Socialbot.
The task is to improve the landing of the socialbot: add more functionality in conversation (including images and probably voice messages sending), add animated avatar of the socialbot personality with a based set of emotions. The task lets you not only demonstrate your development skills but also creativity.
duration: 350 hours
requirements: fluency in TypeScript, Python, understanding of CSS, React + redux or similar state management library + FastAPI
difficulty: medium
See full details about task in the Task Page.
The task is to improve the landing of the socialbot: add more functionality in conversation (including images and probably voice messages sending), add animated avatar of the socialbot personality with a based set of emotions. The task lets you not only demonstrate your development skills but also creativity.
duration: 350 hours
requirements: fluency in TypeScript, Python, understanding of CSS, React + redux or similar state management library + FastAPI
difficulty: medium
See full details about task in the Task Page.
Development of a Dashboard for the Dream Dialog System
The task is to develop a dashboard for the Dream dialog system. Dream Dashboard is required for the following tasks:
duration: 350 hours
requirements: fluency in TypeScript, Python, understanding of CSS, React + redux or similar state management library + FastAPI or Flask, D3 or other JS visualization library
difficulty: medium
See full details about task in the Task Page.
- monitoring the technical status of the system
- dialogue analytics
- displaying dialogs according to conditions and filters
- integration with DF Dashboard to view analytics for individual skills
- search and analytics of bad dialogues, evaluation of dialogues by many parameters
- training and connecting ML models to display additional analytics
duration: 350 hours
requirements: fluency in TypeScript, Python, understanding of CSS, React + redux or similar state management library + FastAPI or Flask, D3 or other JS visualization library
difficulty: medium
See full details about task in the Task Page.
Development of DF Designer
DF Designer is a tool for developing scenario-driven skills for multi-skill AI assistants and simple bots in a visual environment.
DF Designer includes basic skill creation capabilities and advanced functionality such as recommender systems in scenario-driven skills, statistical information, etc.
The GSoC student will have to develop the functionality of the tool for working with the recommender system for bot's responses and the functionality for working with statistics.
duration: 350 hours
requirements: Python, understanding of ASTs, experience in optimizing python code, understanding of graphs, TypeScript, React, CSS, (bonus if familiar with VSCode extension API)
difficulty: medium
See full details about task in the Task Page.
DF Designer includes basic skill creation capabilities and advanced functionality such as recommender systems in scenario-driven skills, statistical information, etc.
The GSoC student will have to develop the functionality of the tool for working with the recommender system for bot's responses and the functionality for working with statistics.
duration: 350 hours
requirements: Python, understanding of ASTs, experience in optimizing python code, understanding of graphs, TypeScript, React, CSS, (bonus if familiar with VSCode extension API)
difficulty: medium
See full details about task in the Task Page.
Dialog Flow Framework and an Integration with External Dialogue Services
Dialog Flow Framework (DFF) is a free and open-source software stack for creating chatbots, released under the terms of Apache License 2.0. DFF can be extended by add-ons, these add-ons are implemented as python packages and distributed by PyPi.
In this task we are going to create several Python packages for integrating DFF with messengers (What's app, Facebook, Telegram, Twillio), social bots (Amazon Alexa, Yandex Alice, Google Assistant), support for connecting to sites, etc.
duration: 350/175 hours
requirements: docker, python, REST API
difficulty: easy
See full details about task in the Task Page.
In this task we are going to create several Python packages for integrating DFF with messengers (What's app, Facebook, Telegram, Twillio), social bots (Amazon Alexa, Yandex Alice, Google Assistant), support for connecting to sites, etc.
duration: 350/175 hours
requirements: docker, python, REST API
difficulty: easy
See full details about task in the Task Page.
Dialog Flow Framework and an Integration with Databases
Dialog Flow Framework (DFF) is a free and open-source software stack for creating chatbots, released under the terms of Apache License 2.0. DFF can be extended by add-ons, these add-ons are implemented as python packages and distributed by PyPi.
In this task we are going to create several Python packages for integrating DFF with databases like Postgresql, ClickHouse and etc for a dialog context storing purpose.
duration: 350/175 hours
requirements: docker, python, REST API
difficulty: easy
See full details about task in the Task Page.
In this task we are going to create several Python packages for integrating DFF with databases like Postgresql, ClickHouse and etc for a dialog context storing purpose.
duration: 350/175 hours
requirements: docker, python, REST API
difficulty: easy
See full details about task in the Task Page.
Dialog Flow Framework and Dialog Exploration and Visualization Utils
Dialog Flow Framework (DFF) is a free and open-source software stack for creating chatbots, released under the terms of Apache License 2.0. DFF can be extended by add-ons, these add-ons are implemented as python packages and distributed by PyPi.
In this task we are going to develop Python packages for dialog data exploration and visualization utils based in DFF to analyze user behavior by using ML annotators, statistics methods based on data from databases.
duration: 350/175 hours
requirements: docker, python, REST API
difficulty: medium
See full details about task in the Task Page.
In this task we are going to develop Python packages for dialog data exploration and visualization utils based in DFF to analyze user behavior by using ML annotators, statistics methods based on data from databases.
duration: 350/175 hours
requirements: docker, python, REST API
difficulty: medium
See full details about task in the Task Page.
We want to inform you on how we would like to see the development of your application. See the guide.
GSOC NEWS
Have a question? contact us via