Natural Language Processing Centre

Our work mainly includes: large language models (LLMs), their training and application with textual and multimodal data (e.g., image, sound, and text), the creation and management of text corpora, i.e., storing and retrieving large textual data, knowledge representation, e.g., creating knowledge bases from texts, representation of meaning in natural language expressions for determining text characteristics (such as topics, sentiment, stylistic features, and authorship detection), lexical databases, i.e., software for creating dictionaries, including multimodal data, and the development of dialogue systems or programming of social robots.