2016 International Conference on Big Data and Smart Computing (BigComp) (2016)
Hong Kong, China
Jan. 18, 2016 to Jan. 20, 2016
Jiyeon Choi , Knowledge Service Engineering, KAIST, Daejeon, Korea
Youkyoung Park , Knowledge Service Engineering, KAIST, Daejeon, Korea
Mun Yi , Knowledge Service Engineering, KAIST, Daejeon, Korea
Query expansion is a well known method widely used to improve the efficiency and precision of information retrieval in diverse fields. However, information retrieval in the medical domain still confronts many challenges due to the vastness of jargons and inconsistency of terms, leading to poor performance in information retrieval. To circumvent these problems, the main strategy that has been used is to rely on medical ontologies known as an intensional approach despite the fact that it lacks range of expressions. In contrast, an extensional approach is based on external resources such as documents, notwithstanding its own weaknesses. Thus in this paper we propose a hybrid approach, which combines the two approaches along with a refinement technique, in order to overcome each approach's weaknesses while creating a synergistic effect that maximizes each approach's strengths. The effectiveness of this framework is tested through an experiment using TREC-CDS Track 2014 data. Based on the positive results, we suggest this hybrid approach as a viable solution in query expansion for the medical domain.
Ontologies, Unified modeling language, Feature extraction, Biomedical imaging, Semantics, Mathematical model
Jiyeon Choi, Youkyoung Park and Mun Yi, "A hybrid method for retrieving medical documents with query expansion," 2016 International Conference on Big Data and Smart Computing (BigComp)(BIGCOMP), Hong Kong, China, 2016, pp. 411-414.