Table 2.

Evaluation data sets and samples for different tasks.

Task	Data set	Data set example	Samples
Clinical sense disambiguation	CASIa	The abbreviation “CRb” can refer to “cardiac resuscitation” or “computed radiography.”	11 acronyms from 55 notes
Biomedical evidence extraction	EBMc-NLPd	Identifying panic, avoidance, and agoraphobia (psychological interventions)	187 abstracts and 20 annotated abstracts
Coreference resolution	CASI	Resolving references to “the patient” or “the study” within a clinical trial report.	105 annotated examples
Medication status extraction	CASI	Identifying that a patient is currently taking insulin for diabetes.	105 annotated examples with 340 medication status pairs
Medication attribute extraction	CASI	Identifying dosage, frequency, and route of a medication for a patient.	105 annotated examples with 313 medications and 533 attributes

^aCASI: clinical abbreviation sense inventories.

^bCR: cardiac resuscitation.

^cEBM: evidence-based medicine.

^dNLP: natural language processing.