Artificial Intelligence & Language Technologies

The “Artificial Intelligence and Language Technology” department focuses on creating models for understanding and generation of natural language by machine, using technologies of the artificial intelligence such as knowledge representation in terms of knowledge graphs, modelling and processing of language data using machine learning, including deep neural networks and large language models (based on Transformers). We consider the natural language not only as text and speech, but also as a manifestation in context. The context includes situations and factors from the outer world, such as images, world knowledge and knowledge about specific situations, knowledge of grammatical and semantic characteristics, as well as about the functions of the language itself, etc.

Language resources and technologies are mainly used for implementation of applications related to understanding and generation of natural language. But they also support research in the field of Social sciences and Humanities, as well as the construction of better large language models in the field of generative artificial intelligence. Resources and technologies are also used for: detecting positive and negative stereotypes and/or biases in data; Dealing with undesired errors in models; Identifying missing types of knowledge; and for the training of artificial intelligence based on small sets of examples.

In our work, we exploit hybrid approaches which combine neural networks models with symbolic ones to achieve better synergy in both areas of research – artificial intelligence and natural language processing.

Language resources and technologies are the basis for applications such as communication with artificial agents; descriptions of events with a complex structure; extraction and representation of knowledge from text, decision support of users; augmentation of document content with additional knowledge and more. Thus, through the usefulness, accuracy and speed of various interdisciplinary applications for the benefit of society, we create good practices with social and scientific importance.