Semi-supervised cause identification from aviation safety reports

To improve the performance of a cause identification system for the minority classes, this work presents a bootstrapping algorithm that automatically augments a training set by learning from a small amount of labeled data and a large amount of unlabeled data.

Abstract

We introduce cause identification, a new problem involving classification of incident reports in the aviation domain. Specifically, given a set of pre-defined causes, a cause identification system seeks to identify all and only those causes that can explain why the aviation incident described in a given report occurred. The difficulty of cause identification stems in part from the fact that it is a multi-class, multilabel categorization task, and in part from the skewness of the class distributions and the scarcity of annotated reports. To improve the performance of a cause identification system for the minority classes, we present a bootstrapping algorithm that automatically augments a training set by learning from a small amount of labeled data and a large amount of unlabeled data. Experimental results show that our algorithm yields a relative error reduction of 6.3% in F-measure for the minority classes in comparison to a baseline that learns solely from the labeled data.