Ontology learning in practice : using semantics for knowledge grounding

Abstract

This chapter presents research results, showing the use of ontology learning for knowledge grounding in e-learning environments. The established knowledge representation model is organized around actions, as the main elements linking the acquired knowledge with knowledge-based real-world activities. A framework for action ontology building from domain-specific corpus texts is suggested, utilizing different Natural Language Processing (NLP) techniques, such as collocation extraction, frequency lists, word space model, etc. The suggested framework employs additional knowledge sources of WordNet and VerbNet with structured linguistic and semantic information. Results from experiments with crawled chemical laboratory corpus texts are presented.