Штучний інтелект

Науковий журнал

ISSN 2710-1673

ONLINE: ISSN 2710-1681

Виберіть свою мову


Technology of Knowledge Extraction on the Base of Extended Semantic Networks

Кузнєцов І.П.1, Шарнін М.М.1, Мацкевич А.Г.1
1 Інститут проблем інформатики РАН

Повний текст (PDF)

УДК: 681.3.01
Мова публікації: Російська
Stuc. intelekt. 2012; 17; (4):190-203

Анотація: The paper is devoted to the extracting of knowledge structures from the natural language texts, i.e. information objects (“Named Entities”), their features, relationships, and participation in the actions and events. For this purpose, the language used for knowledge representation (extended semantic networks/ESN) and tools for processing (language for structure conversion LSC) are considered. On this base, the new technologies are proposed. These technologies have the following features: extraction from the texts of knowledge structures that represent the links of named entities and their participation in actions and events. For the knowledge extraction the unique semantic-oriented language processor (LP) are designed. Processor LP provides the deep analysis of NL-texts and revealing set of objects together with their structures. Processor LP is controlled by the linguistic knowledge, which are declarative structures (on ESN) and which provides the quick tuning of LP on subject area and language, both Russian and English.

Ключові слова: knowledge extraction from texts, semantic-oriented linguistic processor, extended semantic networks, knowledge structure processing

Посилання:

Переглянути повний текст статті (PDF)