Modern world is built around knowledge and it is impossible to think without knowledge. As the volume of online information continues to grow, the need for innovation in the domain of knowledge extraction is getting more and more pressing. This is equally important for general-purpose sources as well as for domain-specific information, e.g., for physics or computer science. While there are many solutions providing effective information management for structured, domain-specific data, large amounts of information still remain in unstructured form (e.g., text) and are hence difficult to process.
My research is focused on developing new methods providing effective knowledge extraction, processing and discovery for unstructured technical sources. Specifically, my focus is on performing named-entity recognition and disambiguation for scientific documents, establishing semantic relationships between scientific entities, and providing effective document discovery based on those entities.
My full CV is available on: careers.stackoverflow.com/prokofyev
Semantic Web; Topic modeling; Text classification; Word Sense Disambiguation