Semantic Technologies for Ontology Population and Deep Natural Language Processing

Natural Language Processing is a field focused on speech and text processing making unstructured information in it accessible for computer applications. NLP is a vast subject integrating models and methods of language theory, mathematics, computer science and cognitive sciences. Traditional tasks in NLP include text spell-checking and tokenization, tagging, parsing, semantic analysis for information extraction and knowledge bases population.

Projects of the ISST Laboratory are focused on fact extraction and automatic ontology and knowledge bases population using semantic technologies for deep linguistic processing in dialogue and expert systems. The project on parser development for Russian spontaneous speech got RFBR support since 2016.