Online Biomedical Concept Annotation Using Language Model Mapping

We report the results of applying language technology to the bioinformatics problem of online concept annotation of biomedical text. We extend our concept annotator, CONANN, to find biomedical concepts in using concept language models. The goal of CONANN is to improve annotation speed without losing annotation accuracy as compared to offline systems, facilitating the use of concept annotation in online environments. Intrinsic and extrinsic evaluations show accuracy competitive with a state-of-the-art biomedical text concept annotator with a speed improvement of more than four times.