Michael Sokolov, CTO, Dex Technologies
Michael is a data strategist, NLP expert and systems architect. Successfully implemented dozens of large projects, including projects for the US government and achieved state-of-the-art results in QA systems.
He runs his own data science R&D company and coordinates several companies in the development and delivery of AI software and solutions for IT, Healthcare, Finances, Cybersecurity, Retail and other spheres.
Eugene Zarzhytskyi, Co-founder, Dex Technologies
Eugene is Dex Technologies co-founder and a Senior Software Engineer with 20+ years of programming experience in different programming languages. He is an ardent supporter of the open source ideology who loves quality code. Eugene has been a lead architect on most of the DEX projects for a long time. Eugene has a second degree in Project Management which allows him to organize the development process efficiently.
In the workshop, we will consider some original approaches to building pipelines from text generation:
? lecturers will show you some interesting tricks with GPT2, XLNet, and other models;
? the workshop will be in interactive form with practical tasks that you will perform in Google Colab with the lecturer’s help;
? together we will consider the main approaches to text generation;
? we will understand how the results produced by different models differ;
? we will visualize the results for better understanding;
? we will collect own pipeline from pre-prepared components and dataset to generate text;
? As a result, each participant will have his/her own unique result and interesting experience.
The most creative participants will receive small prizes.
For the workshop, you will need: knowledge of Python, google account, google colab / jupyter notebook, knowledge of English — intermediate +.
