W Hersh1, S Price, L Donohoe. 1. Division of Medical Informatics & Outcomes Research, Oregon Health Sciences University, Portland, Oregon, USA.
Abstract
OBJECTIVES: Assess query expansion using thesaurus relationships and definitions in the UMLS Metathesaurus for improving searching performance. METHODS: The queries from a MEDLINE test collection (OHSUMED) were expanded using synonym, hierarchical, and related term information as well as term definitions from the UMLS Metathesaurus. Documents were retrieved from a word-statistical retrieval system and assessed for recall and precision based on relevance judgments from the test collection. RESULTS: All types of query expansion degraded aggregate retrieval performance as measured by recall and precision, although 38.6% of the queries with synonym expansion and up to 29.7% of the queries with hierarchical expansion showed improvement. CONCLUSIONS: Thesaurus-based query expansion causes a decline in retrieval performance generally but improves it in specific instances. Further research must focus on identifying instances where performance improves and how it can be exploited by real users.
OBJECTIVES: Assess query expansion using thesaurus relationships and definitions in the UMLS Metathesaurus for improving searching performance. METHODS: The queries from a MEDLINE test collection (OHSUMED) were expanded using synonym, hierarchical, and related term information as well as term definitions from the UMLS Metathesaurus. Documents were retrieved from a word-statistical retrieval system and assessed for recall and precision based on relevance judgments from the test collection. RESULTS: All types of query expansion degraded aggregate retrieval performance as measured by recall and precision, although 38.6% of the queries with synonym expansion and up to 29.7% of the queries with hierarchical expansion showed improvement. CONCLUSIONS: Thesaurus-based query expansion causes a decline in retrieval performance generally but improves it in specific instances. Further research must focus on identifying instances where performance improves and how it can be exploited by real users.
Authors: Qing T Zeng; Jonathan Crowell; Robert M Plovnick; Eunjung Kim; Long Ngo; Emily Dibble Journal: J Am Med Inform Assoc Date: 2005-10-12 Impact factor: 4.497
Authors: Robert Moskovitch; Susana B Martins; Eytan Behiri; Aviram Weiss; Yuval Shahar Journal: J Am Med Inform Assoc Date: 2007-01-09 Impact factor: 4.497
Authors: Charles A Sneiderman; Dina Demner-Fushman; Marcelo Fiszman; Nicholas C Ide; Thomas C Rindflesch Journal: J Am Med Inform Assoc Date: 2007-08-21 Impact factor: 4.497
Authors: David A Hanauer; Danny T Y Wu; Lei Yang; Qiaozhu Mei; Katherine B Murkowski-Steffy; V G Vinod Vydiswaran; Kai Zheng Journal: J Biomed Inform Date: 2017-01-25 Impact factor: 6.317