A semi-informative aware approach using topic model for medical search

  • Qinmin Vivian Hu
  • , Liang He
  • , Mingyao Li
  • , Jimmy Xiangji Huang
  • , E. Mark Haacke

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

We propose a semi-informative aware approach using the topic model on query expansion problem in the biomedicine domain. The demographics and disease information is applied to semi-structure the topic model as the 'known' label, compared to the traditional latent topics in topic modelling. Then, we suggest to select three terms from the top ranked documents to expand the query, based on the assumption in the pseudo relevance feedback method that the top ranked results in the first retrieval around are relevant. After that, we conduct the experiments on the TREC medical records data sets with extensive analysis and discussions. Numerically, we achieve the improvements of 7.41% on MAP, 9.29% on Bpref and 5.60% on P@10 respectively over the strong baselines.

Original languageEnglish
Title of host publicationProceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014
EditorsHuiru Zheng, Xiaohua Tony Hu, Daniel Berrar, Yadong Wang, Werner Dubitzky, Jin-Kao Hao, Kwang-Hyun Cho, David Gilbert
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages320-324
Number of pages5
ISBN (Electronic)9781479956692
DOIs
StatePublished - 29 Dec 2014
Event2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014 - Belfast, United Kingdom
Duration: 2 Nov 20145 Nov 2014

Publication series

NameProceedings - 2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014

Conference

Conference2014 IEEE International Conference on Bioinformatics and Biomedicine, IEEE BIBM 2014
Country/TerritoryUnited Kingdom
CityBelfast
Period2/11/145/11/14

Fingerprint

Dive into the research topics of 'A semi-informative aware approach using topic model for medical search'. Together they form a unique fingerprint.

Cite this