DeepPavlov.ai

We are on a mission of solving conversational intelligence. We make research, open-source state-of-the-art approaches to NLP in DeepPavlov conversational AI technology stack, and apply our research to the real world problems. Our goal is to enable AI-application developers and researchers with the state-of-the-art tools for creation of next generation conversational systems. Currently, our leading product, DeepPavlov Library, has amassed about 7K stars on GitHub, about 500K downloads from PyPi, and its most popular model has a steady 1M+ downloads on HuggingFace on a monthly basis. DeepPavlov Library is an open-source conversational AI library built on PyTorch and Keras, designed for: -development of production ready chat-bots and complex conversational systems, -NLP and dialog systems research. We also invest in standardisation of dialogue systems evaluation tools in order to make such systems directly comparable. We organise the Conversational Intelligence Challenges at NIPS in partnership with Facebook AI Research, University of Montreal, McGill and Carnegie Mellon University. We share knowledge in conversational AI through DeepHack Hackathons and Science School. We are open to industrial, technological and academic collaboration.