ISSN 1991-2927
 

ACP № 4 (58) 2019

Author: "Ilya Alekseevich Andreev"

Ilya Alekseevich Andreev, Ulyanovsk State Technical University, a student at the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; an author of several articles in the field of information extraction from text. [e-mail: ares-ilya@yandex.ru]I. Andreev,

Vitaliy Aleksandrovich Bashaev, Ulyanovsk State University, a post-graduate student; graduated from the Faculty of Linguistics and International Cooperation of Ulyanovsk State University; an author of several articles in the field of information extraction from text. [e-mail: perevod73@yandex.ru]V. Bashaev,

Victor Victorovich Klein, Ulyanovsk State Technical University, a student at the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; an author of several articles in the field of information extraction from text. [e-mail: vikklein93@gmail.com]V. Klein,

Vadim Sergeevich Moshkin, Ulyanovsk State Technical University, a post-graduate student at the Department of Information Systems of Ulyanovsk State Technical University; graduated from the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; an author of articles in the field of data analysis intelligence systems. [e-mail: postforvadim@yandex.ru]V. Moshkin,

Nadezhda Glebovna Yarushkina, Ulyanovsk State Technical University, Doctor of Engineering, Professor, Head of the Department of Information Systems at Ulyanovsk State Technical University; an author of more than 250 papers in the field of soft computing, fuzzy logic, and hybrid systems. [e-mail: jng@ulstu.ru]N. Yarushkina

A Semantic Metric of the Termhood Based on the Subject Area Ontology 38_10.pdf

The article describes a semantic metric for a retrieval of a list of terms from the texts of a specific knowledge domain, based on the analysis of its ontology. A formal model of the used OWL-ontology, as well as models and algorithms for the degree evaluation of a word termhood or word combinations of text arrays are presented. In addition, the evaluation metrics of the presented semantic algorithms performance are given. The implementation of the formal models of a domain knowledge representation in an ontological form and the algorithms developed in the software system for the terminology extraction from the text is considered. In conclusion, the results of the computational experiments performed for the extraction of terms based on the ontology of the NC turning-milling machine operation from the texts of an appropriate knowledge domain are provided. A conducted research is summarized. The most efficient algorithms for the degree evaluation of a word termhood or word combinations are revealed, and a perspective for further scientific research in this area is examined.

Term extraction, semantic metric, ontology.

2014_ 4

Sections: Artificial intelligence

Subjects: Artificial intelligence.


Ilia Alekseevich Andreev, Ulyanovsk State Technical University, a student of the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; an author of several articles in the field of information extraction from a text. [e-mail: ares-ilya@yandex.ru]I. Andreev,

Vitalii Aleksandrovich Bashaev, Ulyanovsk State Technical University, a post-graduate student, graduated from the Faculty of Linguistics and International Cooperation at Ulyanovsk State University; an author of articles in the field of information extraction from a text. [e-mail: perevod73@yandex.ru]V. Bashaev,

Victor Victorovich Klein, Ulyanovsk State Technical University, a student of the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; an author of several articles in the field of information extraction from a text. [e-mail: vikklein93@gmail.com]V. Klein,

Nadezhda Glebovna Iarushkina, Ulyanovsk State Technical University, Doctor of Engineering, Professor, Head of the Department of Information Systems at Ulyanovsk State Technical University; an author of more than 250 papers in the field of soft computation, fuzzy logic, and hybrid systems. [e-mail: jng@ulstu.ru]N. Iarushkina

Combining Statistic and Linguistic Methods to Exstract Two-word Terms From a Text 34_11.pdf

This article contains the experiment results on the combination of linguistic and statistical methods for extraction of two-word terms from a text on "CnC Machines" discipline. Along with the experiment and the results, a special attention is paid to the description of the developed software architecture.

Term extraction, linguistic method, statistic method, bigrams frequency.

2013_ 4

Sections: Artificial intelligence system

Subjects: Artificial intelligence, Information systems.


© FRPC JSC 'RPA 'Mars', 2009-2018 The web-site runs on Joomla!