Abstract
In the aviation safety research domain, cause identi?cation refers to the task of identifying the possible causes responsible for the incident described in an aviation safety incident report. This task presents a number of challenges, including the scarcity of labeled data and the dif?culties in ?nding the relevant portions of the text. We investigate the use of annotator rationales to overcome these challenges, proposing several new ways of utilizing rationales and showing that through judicious use of the rationales, it is possible to achieve significant improvement over a unigram SVM baseline.