From 26 to 29 March, a week of NLP will be held in Yandex, organized jointly by the School of Data Analysis and Yandex.Research. This is a four-day intensive course designed for developers and researchers who are familiar with Natural Language Processing and in-depth training.
Lecturers of the course: Mirella Lapata, Professor at the School of Computer Science at the University of Edinburgh, and Wilker Aziz, Associate Professor (Assistant Professor) at the Institute of Logic, Language and Computing at the University of Amsterdam. Lectures will be given in English in the evening.

')
As part of the course you will learn:
- How latent variables are used in text analysis tasks and how to build deep generative models with latent discrete variables.
- What is semantic parsing: how to build a formal representation of the meaning of the text, while extracting implicit values.
Timetable of classes:
26.03 - 18: 00-21: 00 - Latent variable models and posterior inference (Wilker Aziz)
27.03 - 18: 00-21: 00 - Deep generative models for NLP (Wilker Aziz)
March 28 - 18: 00-21: 00 - Advanced topics (Wilker Aziz)
March 29 - 18: 00-21: 00 - Semantic parsing (Mirella Lapata)
Intensive will be useful if you have the following knowledge:
- NLP: good knowledge and experience.
- Machine learning: good knowledge in machine learning and depth learning.
- Mathematics: knowledge of linear algebra and probability theory.
- Programming: Python and knowledge of the PyTorch library.
- English: Free understanding of professional English.
To take part in the event, you must
fill out a questionnaire . The event is free, but the number of seats is limited. It is necessary to fill in the questionnaire before March 18. The answer for your application will come no later than March 20 to the mail specified during registration. Any questions about the event can be sent to shad@yandex-team.ru with the mark Yandex NLP week.