O.O. Dmytrenko, D.V. Lande
Building of semantic networks to determine the degree of text similarity or difference
//
Теоретичнi i прикладнi проблеми фiзики, математики та iнформатики:
матерiали XX Всеукра╖нсько╖ науково-практично╖ конференцi╖ студентiв, аспiрантiв та молодих вчених (15 червня 2022 р., м. Ки╖в, Укра╖на).
- Ки╖в : КПI iм. Iгоря Сiкорського, Вид. "Полiтехнiка", 2022. - C. 197-292
|
Abstract. The paper presents a method for comparing text documents based on the building and comparison of the corresponding semantic networks. This method can be the basis for building systems for comparing legal documents in the framework of parliamentary control. The algorithm for building semantic networks as one of the types of ontologies is also considered. This algorithm can also be used in systems of automatic abstracting of legal information in order to generate concise information-rich reports, brief annotations or digests. The proposed method can be used in the process of processing queries during information retrieval, providing the ability to determine the degree of similarity or difference in the structure and semantics of texts. Keywords: semantic network, natural language processing, legal information, horizontal visibility network, text comparison, computational linguistics |
