CRCTOL: A semantic‐based domain ontology learning system

Abstract

Domain ontologies play an important role in supporting knowledge-based applications in the Semantic Web. To facilitate the building of ontologies, text mining techniques have been used to perform ontology learning from texts. However, traditional systems employ shallow natural language processing techniques and focus only on concept and taxonomic relation extraction. In this paper we present a system, known as Concept-RelationConcept Tuple-based Ontology Learning (CRCTOL), for mining ontologies automatically from domain-specific documents. Specifically, CRCTOL adopts a full text parsing technique and employs a combination of statistical and lexico-syntactic methods, including a statistical algorithm that extracts key concepts from a document collection, a word sense disambiguation algorithm that disambiguates words in the key concepts, a rule-based algorithm that extracts relations between the key concepts, and a modified generalized association rule mining algorithm that prunes unimportant relations for ontology learning. As a result, the ontologies learned by CRCTOL are more concise and contain a richer semantics in terms of the range and number of semantic relations compared with alternative systems. We present two case studies where CRCTOL is used to build a terrorism domain ontology and a sport event domain ontology. At the component level, quantitative evaluation by comparing with TextTo-Onto and its successor Text2Onto has shown that CRCTOL is able to extract concepts and semantic relations with a significantly higher level of accuracy. At the ontology level, the quality of the learned ontologies is evaluated by either employing a set of quantitative and qualitative methods including analyzing the graph structural property, comparison to WordNet, and expert rating, or directly comparing with a human-edited benchmark ontology, demonstrating the high quality of the ontologies learned.

Ontology Supported Information Systems: A Review

“…This system was implemented and tested in the Library of National Chung Hsing University in Taiwan. Jiang and Tan (2010) objected that traditional ontology construction systems employ shallow natural language processing techniques and focus only on concept and taxonomic relation extraction. To overcome this drawback, the authors proposed a system, known as Concept-Relation-Concept Tuple-based Ontology Learning (CRCTOL), for mining ontologies automatically from domain specific documents.…”

A Pattern for Concept Identification from English Translated Quran

“…The use of linguistic technique in an ontology learning system such as CRCTOL, mainly depends on pattern and POS rule to detect multi terms from text to be concepts [15]. The performance of the extraction has been compared to other ontology learning system which is Text2Onto.…”

“…Concept can be a single term or multi term [14] [15]. Linguistic and statistical methods are popular methods in ontology learning [12].…”

From text mining to knowledge mining: An integrated framework of concept extraction and categorization for domain ontology

“…Linguistic techniques (Hamish Cunningham, 2005;Hobbs, Appelt, Bear, & Tyson, 1992) based on the premise that by using syntactic analysis, the relationship between words can be made out. Statistical approaches (Cimiano & Völker, 2005;Jiang & Tan, 2010;Wong, Liu, & Bennamoun, 2007) used statistical measures to find out frequent terms in domain related documents. These frequent terms represent important concepts and frequent occurrence of these concepts indicates the relationship among them.…”

“…Jiang and Tan (Jiang & Tan, 2010) proposed a system, Concept-Relation-Concept Tuple based Ontology Learning (CRCTOL) for ontology learning. This system follows a multiple corpus based approach for key concept extraction.…”