Automatic Extraction of New Concepts from Domain-Specific Terms

Autor: N. A. Astrakhantsev
Jazyk: English<br />Russian
Rok vydání: 2018
Předmět:
Zdroj: Труды Института системного программирования РАН, Vol 25, Iss 0, Pp 167-178 (2018)
Druh dokumentu: article
ISSN: 2079-8156
2220-6426
Popis: This paper describes a novel approach for recognition of domain-specific terms that exist in the knowledge base but represent new concepts. Our method can be applied to informal knowledge bases – it requires only semantic similarity between concepts and statistics of terms extracted from the corpus. We show that our method outperforms existing approaches and improves precision of word sense disambiguation algorithm.
Databáze: Directory of Open Access Journals