Evaluating Context Features for Medical Relation Mining

The paper describes a set of experiments aimed at identifying and evaluating context features and machine learning methods to identify medical semantic relations in texts. We use manually constructed lists of pairs of MeSH-classes that represent specific relations, and a linguistically and semantically annotated corpus of medical abstracts to explore the contextual features of relations. Using hierarchical clustering we compare and evaluate linguistic aspects of relation context and different data representations. Through feature selection on a small data set we also show that relations are characterized by typical context words, and by isolating these we can construct a more robust language model representing the target relation. Finally, we present graph visualization as an alternative and promising way of data representation facilitating feature selection.