Machine Learning for Rhetorical Figure Detection: More Chiasmus with Less Annotation
Marie Dubremetz, Joakim Nivre · DSpace repository (University of Tartu) · 2017
Figurative language identification is a hard problem for computers.In this paper we handle a subproblem: chiasmus detection.By chiasmus we understand a rhetorical figure that consists in repeating two elements in reverse order: "First shall be last, last shall be first".Chiasmus detection is a needle-in-the-haystack problem with a couple of true positives for millions of false positives.Due to a lack of annotated data, prior work on detecting chiasmus in running text has only considered hand-tuned systems.In this paper, we explore the use of machine learning on a partially annotated corpus.With only 31 positive instances and partial annotation of negative instances, we manage to build a system that improves both precision and recall compared to a hand-tuned system using the same features.Comparing the feature weights learned by the machine to those give by the human, we discover common characteristics of chiasmus.