Query Expansion Using SNOMED-CT and Weighing Schemes

Abstract

Despite all the advancements that have been made in the field of Information Retrieval there are still so many challenges. These challenges are magnified when the information that is being retrieved is in a specialized domain such as healthcare. In order to tackle these challenges and encourage research in these domains, TREC (Text RETrival Conference) has instituted a Clinical Track in 2014. This paper is the result of participation in 2014 TREC Clinical Track. It entails the approach and the results that were obtained by utilizing Ontology to expand the original topics. Ontology was used in order to improve the quality of the terms present in the queries or topics, so that the queries are better structured, and they can better target documents of interest. The value that each term brings to the result was measured by way of weighing method algorithms in the retrieval system, BM25 and InL2c1. For this research, we have used SNOMED-CT along with UMLS Methathesaurus as our ontology in medical domain to expand the queries.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2014
Accession Number
ADA618632

Entities

People

  • Afshin Deroie
  • Dawit Girmay

Organizations

  • University of York

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Abstracts
  • Automatic
  • Computer Science
  • Databases
  • Digital Information
  • Hypertension
  • Information Operations
  • Information Retrieval
  • Language
  • Models
  • Ontologies
  • Pain
  • Standards
  • Test And Evaluation
  • Universities

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Information Retrieval
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval