Presentation:
Computational Rhetoric Approach to Solving Complex NLP Tasks

Computational Rhetoric, i.e. processing of non-literal natural language and detection of rhetorical figures, applied to Sentiment Analysis, Offensive language modelling and detection, Legal Tech, Argumentation Mining and other areas of NLP, has the potential to facilitate deeper, automatic understanding in natural language. In this talk, we will show how computational modelling of rhetorical figures and the relations that exist between their building blocks, can help us come closer to achieving that.

Bio

Jelena Mitrović is a Research Group Leader at the Faculty of Computer Science and Mathematics, University of Passau. Her research group CAROLL, funded by the BMBF Programme for supporting Women in AI, focuses on Computational Rhetoric approaches to solving complex Natural Language Processing problems in areas of abusive language detection, argumentation modelling and mining, legal text processing and beyond.

Back to the Summer School 2022 overview