Improving Cause Detection Systems with Active Learning

Isaac Persing and Vincent Ng.
Proceedings of the 2010 Conference on Intelligent Data Understanding, pp. 39-53, 2010.

Click here for the PostScript or PDF version. The talk slides are available here.

Abstract

Active learning has been successfully applied to many natural language processing tasks for obtaining annotated data in a cost-effective manner. We propose several extensions to an active learner that adopts the margin-based uncertainty sampling framework. Experimental results on a cause detection problem involving the classification of aviation safety reports demonstrate the effectiveness of our extensions.

BibTeX entry

@InProceedings{Persing+Ng:10a,
  author = {Isaac Persing and Vincent Ng},
  title = {Improving Cause Detection Systems with Active Learning},
  booktitle = {Proceedings of the 2010 Conference on Intelligent Data Understanding},
  pages = {39--53},
  year = 2010
}