No abstract

Domain specific ontologies can be used to improve both precision and recall of information retrieval systems. One approach in this regard is using query expansion techniques and the other would be introducing a semantic similarity measure for concepts in ontology. Although each approach has its own benefits and drawbacks, query expansion techniques are preferred when the corpus volume is so huge that examining concept pairs between query and documents is not reasonable. In this paper a semantic query expansion algorithm for medical information retrieval is introduced. Proposed approach consists of identifying MeSH (Medical Subject Headings) concepts in user's query and applying expansion algorithm to them. Expansion algorithm is based on the location of concepts in MeSH hierarchy, number of synonyms of each concept and number of terms the concept is made of. Results show improvements over classic method, query expansion using general purpose ontology and a number of other approaches.

There is a huge growth in the volume of published biomedical research in recent years. Many medical search engines are designed and developed to address the over growing information needs of biomedical experts and curators. Significant progress has been made in utilizing the knowledge embedded in medical ontologies and controlled vocabularies to assist these engines. However, the lack of common architecture for utilized ontologies and overall retrieval process, hampers evaluating different search engines and interoperability between them under unified conditions. In this paper, a unified architecture for medical search engines is introduced. Proposed model contains standard schemas declared in semantic web languages for ontologies and documents used by search engines. Unified models for annotation and retrieval processes are other parts of introduced architecture. A sample search engine is also designed and implemented based on the proposed architecture in this paper. The search engine is evaluated using two test collections and results are reported in terms of precision vs. recall and mean average precision for different approaches used by this search engine.

No abstract

No abstract