Abstract: The paper discusses the general architecture of NLU-systems. We focus on three main subjects: target information technology and target knowledge representation language; processing levels interaction and integration; role and proportion of rule-based and corpus-based methods.

Abstract: This article is devoted to some aspects of development a system for managing of graphic documents collections. We describe the administrate and user interfaces of worked system, existing and new image features and their usage in different methods for search and classification, faced problems and solutions to solve them.