Jakub Lengiewicz

Abstract: These days it would not be an exaggeration to say that we live in a world where AI applications are taking over. What is sure that they are impressing the public more and more. Couple years ago, GANs impressed people for creating images which do not exist in reality. The culmination was Dalle2 project which could create a new image from any description one gave to it. With the developments in the Natural Language Understanding now Chatbots can understand and answer questions one asks. Recently, ChatGPT proved it to everyone. Creating new, before non-existing images can be impressing. However, it is a Chatbot, which fascinates human beings the most. Can an algorithm think, communicate, and talk or even may be feel like us? What are the technologies behind it? In this talk I would like to shed a light to the development of Natural Language Technologies starting from the early applications up to the modern deep learning algorithms. I will give a direct intuition and explanation on how algorithms learn languages. Algorithms like Word2Vec and Transformers are not only going to be explained, but I will try to put everything into the landscape of existing technologies, from mathematical and topological point of view.

Dr. Joshgun Sirajzade is a post-doctoral researcher within the Faculty of Science, Technology and Medicine at the University of Luxembourg.