Rhetorical Figure Annotation with XML

Sebastian Ruan, Chrysanne Di Marco, Randy Allen Harris
2016 International Joint Conference on Artificial Intelligence  
There is a driving need to interrogate large bodies of text for pragmatic meaning, e.g., to detect sentiment, diagnose genre, plot chains of reasoning, and so forth. But this type of meaning is often implicit, 'hidden' meaning, evoked by linguistic cues, stylistic arrangement, or argumentation structurefeatures that have hitherto been difficult for Natural Language Processing (NLP) systems to recognize and use. Pragmatic concerns were historically the province of rhetorical studies, and we have
more » ... turned to rhetoric in order to find new solutions to computational pragmatics. This paper highlights a form of rhetorical device that encodes deep levels of pragmatic meaning and yet lends itself to automated detection. These devices are the linguistic configurations known as rhetorical figures, which have been poorly understood and vastly underutilized in Computational Linguistics and Computational Argumentation. We present an annotation scheme using XML for rhetorical figures to make figuration more tractable for NLP, enhancing applications for argument mining, along with a range of other tasks. We also discuss the intellectual and technical challenges involved in figure annotation and the implications for Machine Learning.
dblp:conf/ijcai/RuanMH16 fatcat:wpadgnyc3jfqfo5y2niw4odr2i