An Annotation Tool for Automatically Detecting Rhetorical Figures SYSTEM DEMONSTRATION

Linguistic annotation provides additional information asserted with a particular purpose in a document or other piece of information. It is widely used in various fields, from computing and bioinformatics, through imaging, to law and linguistics. There is also a clear distinction between what is communicated through the written/spoken natural language and how this is passed on. We are studying a new problem in linguistic annotation—annotation of classical rhetorical figures. We have developed a rhetorical annotation tool that can automatically detect patterns of text in which a characteristic syntactic form modifies the standard meanings of words, leading to a change or an extension of meaning. The annotation of rhetorical figures is important not only from a purely linguistic analysis, but also for discovering different styles of writing, purpose, and effect in documents, and for more-sophisticated Natural Language Understanding systems in general.