Generic Semantic Annotation Framework With Integrated Ontology Learner

No Thumbnail Available



Journal Title

Journal ISSN

Volume Title


Addis Ababa University


The Web has become a source of information, where information is provided by humans for humans and its growth has increased the necessity to get solutions that intelligently extract valuable knowledge from existing and newly added web documents with no (minimal) supervisions. However, due to the unstructured nature of existing data on the Web, effective extraction of this knowledge is limited for both human beings and software agents. Thus, our research goal is to design a generic framework that automatically learns ontology from unstructured text and annotate web documents semantically using ontology as a semantic repository. This allows software agents in various fields such as knowledge management, expert systems, and semantic web to understand and process web resources semantically. The proposed framework has the following distinctive features: (1) three granularity level of document tagging (word, sentence and paragraph); (2) structure, language and domain awareness; (3) generic ontology learner integration; (4) annotation maintenance; (5) annotation verification and (6) artificial neural network approaches adoption. We experiment the feasibility of the proposed approach using Amharic news collected from Walta news agency and Amharic Wikipedia. Our result of experimentation shows that the proposed solution exhibits 70.68% of precision, 66.89% of recall and 68.53% of f-measure in semantic annotation for a morphologically complex Amharic language with a limited size dataset. Our experiments demonstrate that the proposed solution has the capability to provide domain and language independent semantic annotation except of general patterns used for ontology learning refinements. Our solution significantly reduces manual annotation and learning cost used for both semantic annotation and ontology learning of web documents with its nature of adaptability with minimal modification. The results have also implied that neural network techniques are promising for both semantic annotation and ontology learning, especially for less resourced languages in comparison to language dependent techniques that have cost of speed and challenge of adaptation into new domains and languages.



Information Extraction, Knowledge Base, Ontology Learning, Semantic Annotation, Semantic Understanding, Semantic Web, Artificial Neural Networks