@InProceedings{bethard-EtAl:2017:SemEval,
  author    = {Bethard, Steven  and  Savova, Guergana  and  Palmer, Martha  and  Pustejovsky, James},
  title     = {SemEval-2017 Task 12: Clinical TempEval},
  booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {565--572},
  abstract  = {Clinical TempEval 2017 aimed to answer the question: how well do systems
	trained on annotated timelines for one medical condition (colon cancer) perform
	in predicting timelines on another medical condition (brain cancer)? Nine
	sub-tasks were included, covering problems in time expression identification,
	event expression identification and temporal relation identification. 
	Participant systems were evaluated on clinical and pathology notes from Mayo
	Clinic cancer patients, annotated with an extension of TimeML for the clinical
	domain. 11 teams participated in the tasks, with the best systems achieving F1
	scores above 0.55 for time expressions, above 0.70 for event expressions, and
	above 0.40 for temporal relations. Most tasks observed about a 20 point drop
	over Clinical TempEval 2016, where systems were trained and evaluated on the
	same domain (colon cancer).},
  url       = {http://www.aclweb.org/anthology/S17-2093}
}