Query specific graph-based query reformulation using UMLS for clinical information access

Biomedical document retrieval requires entity level processing instead of term level. This paper explores the usage and impact of UMLS for entity-based query reformulation in biomedical document retrieval. A novel graph-based approach for query reformulation using UMLS is described herein which queries are expanded using biomedical entities. The proposed method considers UMLS entities from a query with their related entities identified by UMLS and constructs a query-specific graph of biomedical entities for term selection. This query reformulation approach is compared with baseline, pseudo relevance feedback based query expansion approach and state-of-the-art UMLS based query reformulation approaches. The experiments on CDS 2015 and CDS 2016 datasets shows 35% and 45% improvement in retrieval performance, respectively.