The research project comprises statistical approach to analyzing corpus of scientific articles in Computer Science (in English), automatic composing the list of multiword keywords describing the domain, manual building of clusters according to the core component of the phrase and forming a bilingual description for each entry.
The research is held under the supervision of prof. Tamara N....
The project is devoted to the development of the prototype IR system for the search within a document database of a restricted domain. The search method being developed is based on deep semantic approach to indexing documents and applying a domain ontology to refine the query formulation and query-document matching procedure. The focus is on comparing the effectiveness of search procedure,...
The project is aimed at the development of an application that helps Russian scientists in writing abstracts for their scientific articles in the English langauge. The outcome of the project is an authoring tool that allows automated generation of sentences in the Russian langauge and automaically compiles a glossary of terms including multi-word lexical units used in the text of the abstracts...