期刊名称:Journal of Theoretical and Applied Information Technology
印刷版ISSN:1992-8645
电子版ISSN:1817-3195
出版年度:2015
卷号:82
期号:2
出版社:Journal of Theoretical and Applied
摘要:The automatic populating of ontologies from pedagogical textbooks is very hard treatment. Several scientific studies are looking to implement solutions based on linguistic tools to automatically or semi-automatically enrich the ontology by the natural language of mathematical text. But there are still difficulties for the extraction of the meaning of mathematical expressions and their relationships. We present in this paper a methodology for populating of Math-Bridge ontology from the mathematical content of analysis, whose goal is the automatic generation of mathematical exercises from ontology populated. The idea is to use lexical and syntactic patterns for extraction and decomposition of instance attributes into linguistic propositions. A syntactic and semantic comparison of attributes allows extracting semantic relations using WordNet ontology for the textual part and Abstract Syntax Tree AST for the logic part. A first implementation for textual part was developed in JAVA, Framework Jena, and SARQL engine for displaying ontology. We envisage in the further research to develop the second part of the prototype (Logical part).
关键词:Ontology; Population; Semantic Web resources; Information Extraction; Enrichment.