Steven Bedrick

Automatic classification of PubMed abstracts with Latent semantic indexing: Working notes

Joel Robert Adams, Steven Bedrick
CLEF 2014 - Working Notes for CLEF 2014 Conference, Jan 2014


The 2014 BioASQ challenge 2a tasks participants with assigning semantic tags to biomedical journal abstracts. We present a system that uses Latent Semantic Analysis to identify semantically similar documents in MEDLINE to an unlabeled abstract, and then uses a novel ranking scheme to select a list of MeSH headers from candidates drawn from the most similar documents. Our approach achieved good precision, but suffered in terms of recall. We describe several possible strategies to improve our system's performance.

Back to List