DeepPavlov.ai

Active

At DeepPavlov, our investments are spread across 3 parts of the technology stack, including Library, Dream, and Agent. All of these projects are focused on enhancing and strengthening our Conversational AI stack, with each contributing corresponding components.

DeepPavlov can be used for many useful applications, including:

  • process automation of call centers and customer service,
  • development question answering systems at any scale,
  • sentiment classification of customer review,
  • production-ready dialog system,
  • applied NLP research and others.

Overview

DeepPavlov Library is a foundation for our framework. DeepPavlov is an open- source framework for building chatbots and virtual assistants. It comes with a set of predefined components for solving Natural Language Processing (NL) related problems and a framework to build a modular pipeline that lets developers and NLP researchers create production-ready conversational skills and complex multi-skill conversational assistants. DeepPalvov Library is based on TensorFlow and Keras. It contains basic NLP components like NER, Entity Linking, KBQA, Go-Bot, and others. 

In our Conversational AI stack, these components: 

  • are used as standalone services used by skills (e.g., KBQA, Wikidata Parser),
  • provide a framework to build goal-oriented skills (Go-Bot),
  • are used as generic annotators (e.g., NER, Entity Linking, Emotion Analysis, etc.)

The developed  DeepPavlov’s models demonstrate a level of quality that is superior or comparable to the existing solutions of the leading companies -Google, Microsoft, IBM, Facebook and others.

DeepPavlov Agent is our multiskill Conversational AI orchestrator that coordinates the entire Conversational AI pipeline of the AI Assistants. It incorporates annotators, skills, Skill & Response Selectors to provide a coherent experience to its users.

DP Library and DP Agent make it easy for beginners and experts to create dialog systems. Additionally, its declarative approach to defining sequences of model execution in config files allows users to track dependencies and provide paths to download the missing trained ML models.

DeepPavlov Dream is a set of our default goal-oriented and chit-chat skills, as well as a number of demo AI Assistants built using components from Library and managed by DeepPavlov Agent. 

Tutorials

Open Source Community


You can read more about us in our official blog. Also, feel free to test our BERT-based models by using our demo. And don’t forget that DeepPavlov has a dedicated forum, where any questions concerning the framework and the models are welcome. Join our official Telegram channel, Twitter, Facebook and Youtube channel to get notified about our updates & news.

Slack ODS.ai: #tool_deeppavlov

Call to action

If you are an ML/NLP engineer, and share our inner passion to push boundaries of Conversational AI, or simply want to make NLP/NLU tools easier to use by the wider community, we welcome you to join our Open Source Community.

Read the blog post to learn more or start contributing right now.

Our Awards

  1. In 2019, the DeepPavlov project won the "Powered by TF Challenge" competition from Google for the best machine learning project that uses the TensorFlow library.
  2. In 2019, DeepPavlov team  was selected to compete in Alexa Prize Socialbot Challenge 3 by Amazon.
  3. In 2019, the DeepPavlov project received the status of the best open source NLP library according to the Open Data Science Awards Russia.
  4. In 2020 DeepPavlov team was selected to compete in Alexa Prize Socialbot Grand Challenge 4 by Amazon.
  5. In 2020 DeepPavlov team won the 1st cycle Up Great technology contest READ//ABLE of the nomination "Grammar.Eng" for texts in English.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.