Comparison of Several Word embedding Sources for Medical Information Retrieval

Julie Budaher, Mohannad Almasri, Lorraine Goeuriot
2016 Conference and Labs of the Evaluation Forum  
This paper describes the participation of MRIM team in Task 3: Patient-Centered Information Retrieval-IRTask 1: Ad-hoc search of CLEF eHealth Evaluation lab 2016. The aim of this task is to evaluate the effectiveness of information retrieval systems when searching for health content on the web. Our submission investigates the effectiveness of word embedding for query expansion in the health domain. We experiment two variants of query expansion method using word embedding. Our first run is a
more » ... line system with default stopping and stemming. The other two runs expand the queries using two different word embedding sources. Our three runs are conducted on Terrier platform using Dirichlet language model.
dblp:conf/clef/BudaherAG16 fatcat:tfbe3euakzb73mq27kwmudjnzu