Paper: Learning to Temporally Order Medical Events in Clinical Text

ACL ID P12-2014
Title Learning to Temporally Order Medical Events in Clinical Text
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2012
Authors

We investigate the problem of ordering med- ical events in unstructured clinical narratives by learning to rank them based on their time of occurrence. We represent each medical event as a time duration, with a correspond- ing start and stop, and learn to rank the starts/stops based on their proximity to the ad- mission date. Such a representation allows us to learn all of Allen?s temporal relations be- tween medical events. Interestingly, we ob- serve that this methodology performs better than a classification-based approach for this domain, but worse on the relationships found in the Timebank corpus. This finding has im- portant implications for styles of data repre- sentation and resources used for temporal re- lation learning: clinical narratives may have different language attributes ...