Concept detection using text exemplars aligned with a specialized ontology

Abstract

Knowledge extraction from text documents requires identifying and classifying semantic content. Utilizing an appropriate domain ontology can facilitate this process if words and phrases can be linked to the classes and relationships within the ontology. This paper presents an exemplar-based algorithm to link text to semantically similar classes within an ontology constructed for the chronic pain medicine domain. Human annotators linked classes to text segments within a random document set for construction of an exemplar dictionary, which we examined for completeness using Zipf plot analysis. An algorithm was created to use this dictionary on previously unseen text to form a map between sentence text and probable class assignments. We performed a 5×5 cross-validation between human and algorithm annotations and examined both ROC and precision versus recall curves to show that the algorithm can identify the many medical and biopsychosocial components from the texts. We briefly describe a use case for detecting pain relief from various interventions utilizing the word-by-class maps. We conclude that an exemplar-based method can be a valuable tool in knowledge extraction from texts that share similar construction, such as medical progress notes.