GRhOOT: Ontology of Rhetorical Figures in German

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 4001–4010 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 4001 GRhOOT: Ontology of Rhetorical Figures in German Ramona K¨uhn, Jelena Mitrovi´c, Michael Granitzer University of Passau Innstrasse 43, 94032 Passau, Germany {ramona.kuehn, jelena.mitrovic, michael.granitzer}@uni-passau.de Abstract GRhOOT, the German RhetOrical OnTology, is a domain ontology of 110 rhetorical figures in the German language. The overall goal of building an ontology of rhetorical figures in German is not only the formal representation of different rhetorical figures, but also allowing for their easier detection, thus improving sentiment analysis, argument mining, detection of hate speech and fake news, machine translation, and many other tasks in which recognition of non-literal language plays an important role. The challenge of building such ontologies lies in classifying the figures and assigning adequate characteristics to group them, while considering their distinctive features. The ontology of rhetorical figures in the Serbian language was used as a basis for our work. Besides transferring and extending the concepts of the Serbian ontology, we ensured completeness and consistency by using description logic and SPARQL queries. Furthermore, we show a decision tree to identify figures and suggest a usage scenario on how the ontology can be utilized to collect and annotate data. Keywords: Ontologies, Language Modelling, Information Extraction, Information Retrieval, Semantics, Semantic Web, Knowledge Discovery/Representation 1. Introduction Rhetorical figures are omnipresent: in advertising, ar- gumentation, fake news, hate speech, music, and in ev- eryday communication. But how can one recognize a rhetorical figure? In her book “Rhetorical Figures in Science”, Fahnestock (2002) has analyzed different definitions of rhetorical figures: she states that most definitions have in common that figures are consid- ered as a “departure from the normal usage”. Quin- tilian (1996) describes a rhetorical figure as a departure from ordinary meaning, syntax, or form. This raises the question, what “ordinary” means, as figures are not ex- clusively used on certain occasions or by specific com- munities, but “across situations and registers” (Fahne- stock, 2002). Fontanier (1968) also describes figures as principles of departure from a simpler expression: for example, the sentence “he is not the brightest bulb in the box” could be replaced by a simpler expression, e.g., “he is stupid”. Rhetorical figures are used to serve a certain commu- nicative function, to increase memorability, or to at- tract the attention of the reader or listener. Depending on the figure, a certain effect is caused. This “form- function correlation” as Giv´on (1991) describes it, was first mentioned by Aristotle in De Partibus Animalium (Aristoteles et al., 1972). Given the large amount of unstructured data generated every day on the Internet, automated text processing in- cluding natural language processing (NLP) techniques and machine learning algorithms has become essential to analyze and understand the human language: For example, using opinion mining or sentiment analysis gives insights into opinions about products, compa- nies, or political parties (Solangi et al., 2018). Another field of application is the detection of …

Content truncated to 500 words