Authors:
Viorica R. Chifu
;
Ioan Salomie
;
Emil Şt. Chifu
and
Corina Grumazescu
Affiliation:
Technical University of Cluj-Napoca, Romania
Keyword(s):
Ontologies, taxonomy learning, unsupervised neural network.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Ontology and the Semantic Web
;
Soft Computing
;
Symbolic Systems
;
Web Information Systems and Technologies
;
Web Interfaces and Applications
;
Web Mining
Abstract:
Ontologies are widely used today in various domains such as information retrieval, semantic Web, NLP tasks or for describing specific domains like certain branches of medicine. While there are many tools that can be used for learning domain ontologies for English, when learning domain specific ontologies for Romanian, we face a lack of available tools and resources. Moreover, due to the complexity of the Romanian grammar, processing of Romanian text corpora is also difficult. This paper focuses on building a domain specific ontology for the Romanian language using machine learning techniques. The taxonomy learning process is based on an unsupervised neural network. The resulting modules are intended to be used for semantic annotations of traceability services in meat industry.