Knowledge-rich temporal relation identification and classification in clinical notes

Abstract

Motivation: We examine the task of temporal relation classification for the clinical domain. Our approach to this task departs from existing ones in that it is (i) 'knowledge-rich', employing sophisticated knowledge derived from discourse relations as well as both domain-independent and domain-dependent semantic relations, and (ii) 'hybrid', combining the strengths of rule-based and learning-based approaches. Evaluation results on the i2b2 Clinical Temporal Relations Challenge corpus show that our approach yields a 17-24% and 8-14% relative reduction in error over a state-of-the-art learning-based baseline system when gold-standard and automatically identified temporal relations are used, respectively.