Temporal Relation Identification and Classification in Clinical Notes
Jennifer D'Souza and Vincent Ng.
Proceedings of the Fourth ACM Conference on Bioinformatics, Computational
Biology and Biomedicine, pp. 392-401, 2013.
Click here for the PDF
version.
The talk slides are available here.
Abstract
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 (1) knowledge-rich, employing sophisticated
knowledge derived from semantic and discourse relations, and
(2) 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 15-21% and 6-13% 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.
Ruleset
The hand-written rules used in the hybrid approach and the pruning heuristics described in this paper are available from this page.
BibTeX entry
@InProceedings{DSouza+Ng:13b,
author = {Jennifer D'Souza and Vincent Ng},
title = {Temporal Relation Identification and Classification in Clinical Notes},
booktitle = {Proceedings of the 4th ACM Conference on Bioinformatics, Computational Biology and Biomedicine},
pages = {392--401},
year = 2013}