Investigating Distributed Approaches to Efficiently Extract Textual Evidences for Biomedical Ontologies
Abstract
Heterogeneous data resources in biomedicine be- come available both in structured and unstructured formats, such as scientific publications and healthcare guidelines com- pared to formal biomedical ontologies and controlled vocabu- laries. Increasing researches focus on bridging the gaps among the heterogeneous data to discovery implicit knowledge. To make this happen, efficient computational approaches are a necessity for applications in such a knowledge- and data- intensive domain. In this paper, we first define a particular task, relation alignment, which is to identify textual evidences for biomedical ontologies. Then, we investigate two parallel ap- proaches for this task over distributed systems and present the details of their implementations. Moreover, we characterize the performance of our methods through extensive experiments, thereby allowing researchers to make a more informed choice in the presence of large-scale biomedical data.