Annotated document: Scoring and ranking method

Abstract

Semantic annotation represents a metadata of the document based on domain ontology. The purpose of this paper is to present semantic similarity document annotation ranking framework given a user's query. The framework features related concepts inclusion and applies appropriate weighting functions. Our aim is to rank and score semantic document annotation based on document richness. We also compare our approach with other methods using a research prototype retrieval engine, PicoDoc. The system framework of PicoDoc is based on OCAS2008 ontology. In this experiment, we are using a real-life dataset from news article corpus from ABC and BBC. The experiment shows promising results in retrieving related information using the proposed framework.