Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Analysis of Competency Questions for Automatic Generation of Lexico-Syntactic Ontology Design Patterns. / Ovchinnikova, Kristina; Sidorova, Elena.
2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON). Institute of Electrical and Electronics Engineers (IEEE), 2022. стр. 890-895.Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - Analysis of Competency Questions for Automatic Generation of Lexico-Syntactic Ontology Design Patterns
AU - Ovchinnikova, Kristina
AU - Sidorova, Elena
PY - 2022
Y1 - 2022
N2 - The work considers an approach of automatic generation of lexico-syntactic ontology design patterns based on analysis of competence questions expressed in natural language. Process of the generation of lexico-syntactic patterns includes generation of the scientific dictionary, extraction of the entities of the ontology, formation of the structure of extracted relations, such as Data Property and Object Property, and a set of restrictions, including semantic, grammatical and positional restrictions. We use competency questions for specifying grammatical and positional restrictions and extract the necessary grammatical restrictions for each specific relation. For the experiment, we used the “Decision support in weakly formalized areas” ontology, a corpus of scientific texts of the same subject area. During the experiment, we got the following results: the F1 score was 0.77 for attributes and 0.55 for relations. Comparison of the results obtained for patterns without grammatical restrictions and the results obtained for patterns with grammatical restrictions showed that adding restrictions improves extraction of ontology entities.
AB - The work considers an approach of automatic generation of lexico-syntactic ontology design patterns based on analysis of competence questions expressed in natural language. Process of the generation of lexico-syntactic patterns includes generation of the scientific dictionary, extraction of the entities of the ontology, formation of the structure of extracted relations, such as Data Property and Object Property, and a set of restrictions, including semantic, grammatical and positional restrictions. We use competency questions for specifying grammatical and positional restrictions and extract the necessary grammatical restrictions for each specific relation. For the experiment, we used the “Decision support in weakly formalized areas” ontology, a corpus of scientific texts of the same subject area. During the experiment, we got the following results: the F1 score was 0.77 for attributes and 0.55 for relations. Comparison of the results obtained for patterns without grammatical restrictions and the results obtained for patterns with grammatical restrictions showed that adding restrictions improves extraction of ontology entities.
UR - https://www.scopus.com/inward/record.url?eid=2-s2.0-85147526466&partnerID=40&md5=7b8da2372cc96c912727c7bdcad76d07
UR - https://www.mendeley.com/catalogue/bc2c069e-57ad-3924-8b96-ead098592431/
U2 - 10.1109/sibircon56155.2022.10017011
DO - 10.1109/sibircon56155.2022.10017011
M3 - Conference contribution
SN - 9781665464802
SP - 890
EP - 895
BT - 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)
PB - Institute of Electrical and Electronics Engineers (IEEE)
T2 - 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2022
Y2 - 11 November 2022 through 13 November 2022
ER -
ID: 45969535