Clinical TempEval
This addresses the need for temporal information extraction in clinical text, but it is incremental as it adapts an existing task to a new domain.
The paper introduces the Clinical TempEval task for SemEval-2015, which focuses on identifying and describing events, times, and their relations in clinical text, including six subtasks such as recognizing mentions and identifying relations.
We describe the Clinical TempEval task which is currently in preparation for the SemEval-2015 evaluation exercise. This task involves identifying and describing events, times and the relations between them in clinical text. Six discrete subtasks are included, focusing on recognising mentions of times and events, describing those mentions for both entity types, identifying the relation between an event and the document creation time, and identifying narrative container relations.