Cluster-based query expansion using external collections in medical information retrieval

• Published in: Journal of biomedical informatics Vol. 58; pp. 70 - 79
• Main Authors: Oh, Heung-Seon, Jung, Yuchul
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01-12-2015
• Subjects: Cluster Analysis; External collections; Information Storage and Retrieval; Language models; Models, Theoretical; Query expansion; Query expansion; External collections; Language models
• ISSN: 1532-0464; 1532-0480
• DOI: 10.1016/j.jbi.2015.09.017

[Display omitted]
•We propose a query expansion method which utilizes multiple external collections.•To estimate each relevance model, we use the structure of the external collections.•Our method extends queries effectively by considering related context information.•Exhaustive experiments on three different medical test collections were performed.•We report our lessons learned from dealing with different medical test collections.
Utilizing external collections to improve retrieval performance is challenging research because various test collections are created for different purposes. Improving medical information retrieval has also gained much attention as various types of medical documents have become available to researchers ever since they started storing them in machine processable formats. In this paper, we propose an effective method of utilizing external collections based on the pseudo relevance feedback approach. Our method incorporates the structure of external collections in estimating individual components in the final feedback model. Extensive experiments on three medical collections (TREC CDS, CLEF eHealth, and OHSUMED) were performed, and the results were compared with a representative expansion approach utilizing the external collections to show the superiority of our method.