A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Structuring Operative Notes using Active Learning
2014
Proceedings of BioNLP 2014
Preserved Fulltext
We present an active learning method for placing the event mentions in an operative note into a pre-specified event structure. Event mentions are first classified into action, peripheral action, observation, and report events. The actions are further classified into their appropriate location within the event structure. We examine how utilizing active learning significantly reduces the time needed to completely annotate a corpus of 2,820 appendectomy notes.
doi:10.3115/v1/w14-3410
dblp:conf/bionlp/RobertsHS14
fatcat:6cxxgzq7dvcj5nm5h5xk2pgkma