A combination of neural and semantic networks in natural language processing

Author

Gavrilov, Andrey V.

Author_Institution

Dept. of Comput. Sci., Novosibirsk State Tech. Univ., Russia

Volume

2

fYear

2003

Firstpage

143

Abstract

The architecture of learned software for searching of semantics in text documents is proposed. In a basis of performance and the recognition of NL semantics the following fundamental principles are proposed: 1. Orientation to a recognition of semantics with minimum usage of knowledge about syntax of the language, 2. Creation of hierarchies from concepts with horizontal (associative) links between nodes of these hierarchies as result of processing of text documents, 3. Recognition of words and collocations on maximum similar with usage of neural algorithms. The main algorithms of learning of software and searching of documents are considered. Also the features of learning (creation of knowledge base) of proposed software are analyzed. Now research prototype of software with this architecture is implemented.

Keywords

knowledge based systems; learning (artificial intelligence); natural languages; neural nets; semantic networks; text analysis; NL semantics recognition; artificial intelligence; hybrid intelligent system; knowledge base creation; language syntax; learned software architecture; natural language processing; neural network; semantic network; text document; word recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Science and Technology, 2003. Proceedings KORUS 2003. The 7th Korea-Russia International Symposium on

Print_ISBN

89-7868-617-6

Type

conf

Filename

1222593