Персона:
Гаврилкина, Анастасия Сергеевна

Организационные подразделения

Организационная единица

Институт финансовых технологий и экономической безопасности

Институт финансовых технологий и экономической безопасности (ИФТЭБ) Национального исследовательского ядерного университета "МИФИ" готовит кадры в интересах национальной системы по противодействию легализации (отмыванию) доходов, полученных преступным путем, и финансированию терроризма (ПОД/ФТ). Междисциплинарность образования позволит выпускникам ИФТЭБ НИЯУ МИФИ легко адаптироваться на современном рынке труда и в бизнес-среде.

Фамилия

Гаврилкина

Имя

Анастасия Сергеевна

Полная страница элемента

Результаты поиска

Теперь показываю 1 - 8 из 8

Открытый доступ
Ontology of Properties and its Methods of Use: Properties and Unit extraction from texts
(2020) Maksimov, N.; Gavrilkina, A.; Kuzmina, V.; Borodina, E.; Максимов, Николай Вениаминович; Гаврилкина, Анастасия Сергеевна
© 2020 The Authors. Published by Elsevier B.V.Methods of automatic extraction and identification of properties, quantities and units of measurement from texts are considered. The developed ontology of properties and units of measurement includes both fundamental connections of properties and units of measurement and connections that show the formation of concepts. The technology of property identification is based on fact that semantically significant text elements extracted within the boundaries of one or several sentences forming the semantic neighborhood of the property are correlated with the corresponding components of the ontology, which allows to restore the missing semantic fragments or identify discrepancies in the designations. The results of experimental studies of the effectiveness of the developed tools are presented.
Открытый доступ
Knowledge Representation Models and Cognitive Search Support Tools
(2020) Maksimov, N.; Golitsyna, O. L.; Monankov, K.; Gavrilkina, A.; Максимов, Николай Вениаминович; Голицына, Ольга Леонидовна; Гаврилкина, Анастасия Сергеевна
© 2020 The Authors. Published by Elsevier B.V.The purpose of the work is to develop a cognitive-process-oriented model of data search, as well as tools of human interaction in according to this model. Cognitive search is considered as process of formation of ontology of the subject area (of target object) as a system of three systems (functional, conceptual and terminological). Accordingly, the results and trajectory of information retrieval are a reflection and component of the process of cognition. In order to reduce the dimension of the graph (to perception possibilities) aspect projections operation based on the taxonomy of relationships and entities is used.
Только метаданные
Methods of visual graph-analytical presentation and retrieval of scientific and technical texts
(2021) Maksimov, N. V.; Golitsina, O. L.; Monankov, K. V.; Gavrilkina, A. S.; Максимов, Николай Вениаминович; Голицына, Ольга Леонидовна; Гаврилкина, Анастасия Сергеевна
© 2021 National Research Nuclear University. All rights reserved.The technology of constructing and visualizing a semantic image of the full text of the document represented by the ontology as a system of three systems is offered: Functional, conceptual and terminological. Objects and connections of the functional system correspond to the names of entities and relations extracted from the text; to objects of the conceptual system-descriptors of the thesauri of subject areas. The problem of the variable representation of entities at the sign level is solved using the rules for the formation of phrases of different lengths. Functional relationships are classified according to the taxonomy of functional relationships and are used to construct aspect projections of ontologies. As the data model of the ontology, a labeled directed graph is used, which includes nodes and arcs of different types, which makes it possible to formalize operations on ontologies. Constructing a display of set elements of ontology into graph elements in such way that elements of different sets of different systems are distinguishable, recognizable and depicted in different ways, allows to implement the principle of correspondence of the graphic image with the semantics of the visualized data. Based on the search tasks typology, metaphors for visualizing the ontology graph are proposed: The "pathfinding" metaphor, characterized by the construction of a directed chain of facts, and the "neighborhood analysis" metaphor, which is characterized by the study of the environment (context) of a fact. The technology and software for the construction and variant visualization of the ontology graph have been developed. Examples of using the proposed models for information retrieval through document texts are given.
Только метаданные
On One Approach to the Extraction of Entity and Relationships Names in the Task of Building a Semantic Search Image
(2021) Golitsyna, O. L.; Gavrilkina, A. S.; Голицына, Ольга Леонидовна; Гаврилкина, Анастасия Сергеевна
Methods and tools for identifying names of entities and relationships based on lexical and syntactic templates are considered in the framework of the task of semantic indexing of document texts. The content of the text is considered as a set of elementary facts represented by triplets, including the names of entities and relationships. Relations are divided into immanent, situational, and structural-linguistic. A taxonomy of relations is used to typify situational relations, whose classes include linguistic constructions. Immanent relations are formed on the basis of a network of concepts (thesaurus). A taxonomy of properties and units of measurement is used to identify the properties of entities. The proposed approach allows one to use the names of entities and the names of relationships, as well as elementary facts and complete semantic constructions made up of them, as a search query.
Только метаданные
Onto-Graphic Mechanisms for Deep Semantic Search
(2022) Lebedev, A. A.; Gavrilkina, A. S.; Maksimov, N. V.; Golitsyna, O. L.; Monankov, K. V.; Лебедев, Александр Анатольевич; Гаврилкина, Анастасия Сергеевна; Максимов, Николай Вениаминович; Голицына, Ольга Леонидовна
In human-machine document retrieval frameworks focused on information support for main activity cognitive processes, onto-graph-based mechanisms for deep semantic search are discussed. The mechanisms of the application of examples corresponding to users' cognitive states are given on graphs constructed from full texts. The paper gives a comparative evaluation of graph search mechanisms effectiveness in retrieval tasks, as applied to text reading processes.
Только метаданные
Semantic Generalization Means Based on Knowledge Graphs
(2022) Maksimov, N.; Golitsyna, O.; Gavrilkina, A.; Lebedev, A.; Максимов, Николай Вениаминович; Голицына, Ольга Леонидовна; Гаврилкина, Анастасия Сергеевна; Лебедев, Александр Анатольевич
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.The article proposes approaches to text documents semantic content scaling, presented in a knowledge graph form, in order to reduce a cognitive activity working space. Two scaling types operations on graphs are considered - enlargement as aggregation based on inclusion (part-whole relationship) and generalization based on generic relationships. Examples of declarative means use for the scaling operations implementation - a relationships classification and thesaurus are given.
Только метаданные
Разработка модели и алгоритмов рубрицирования терминов тезауруса
(2015) Гаврилкина, А. С.; Гаврилкина, Анастасия Сергеевна; Голицына Ольга Леонидовна
Только метаданные
Ontograph Cognitive Information Retrieval: Some Experimental Evaluations
(2024) Gavrilkina, A.; Golitsyna, O.; Maksimov, N.; Гаврилкина, Анастасия Сергеевна; Голицына, Ольга Леонидовна; Максимов, Николай Вениаминович