Structural Alignment for Comparison Detection

There tends to be a substantial proportion of reviews that include explicit textual comparisons between the reviewed item and another product. To the extent that such comparisons can be captured reliably by automatic means, they can provide an extremely helpful input to support a process of choice. As the small amount of available training data limits the development of robust systems to automatically detect comparisons, this paper investigates how to use semi-supervised strategies to expand a small set of labeled sentences. Specifically, we use structural alignment, a method that starts out from a seed set of manually annotated data and finds similar unlabeled sentences to which the labels can be projected. We present several adaptations of the method to our task of comparison detection and show that adding the found expansion sentences slightly improves over a non-expanded baseline in low-resource settings, i.e., when a very small amount of training data is available.