Nay Lynn (graduate student, Kursk state university)
|
The article analyzes one of the ways of clustering documents. Approaches to the implementation of this method are determined. Clustering of the text by traditional methods is carried out on the basis of syntactic information, rather than semantic information. Therefore, the clustering system does not under-stand the meaning of words, and there are synonyms and polysemy in the doc-uments. But there are other problems that lead to data loss and errors in in-formation. When an ontology is replaced by the same semantically word, there is a possibility of data loss. This article proposes a new generalized clustering method that uses Wikipedia concepts and Wikipedia categories.
Keywords:clustering, ontology, search, semantic weight
|
|
|
Read the full article …
|
Citation link: Nay L. Clustering of documents based on ontology // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2017. -№09. -С. 38-42 |
|
|