Papers by Ramona Kühn
GRhOOT: Ontology of Rhetorical Figures in German (2022.lrec-1)
Copied to clipboard
| Challenge: | GRhOOT is a domain ontology of rhetorical figures in the German language . the goal is to allow for easier detection of non-literal language based tasks . |
| Approach: | GRhOOT is a domain ontology of 110 rhetorical figures in the german language . the goal is to allow for easier detection and sentiment analysis . |
| Outcome: | The ontology of rhetorical figures in the German language is based on 110 rhetorical figure domains . the goal is to make the ontologies more accurate and to allow for easier detection . |
Using Pre-Trained Language Models in an End-to-End Pipeline for Antithesis Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Rhetorical figures are a "departure from the normal usage" of language . features of metaphors, irony and sarcasm enhance performance of several NLP tasks. |
| Approach: | They propose a pipeline approach to detect rhetorical figures using large language models by splitting text into phrases and identifying parallel phrases with a syntactically parallel structure. |
| Outcome: | The proposed approach outperforms state-of-the-art methods by an F1 score of 65.11 %. |
Enhancing Rhetorical Figure Annotation: An Ontology-Based Web Application with RAG Integration (2025.coling-main)
Copied to clipboard
| Challenge: | Rhetorical figures are used to convey subtle, implicit meanings or to emphasize statements. |
| Approach: | They propose a web application that facilitates the identification and annotation of German rhetorical figures. |
| Outcome: | The proposed application improves the user experience with Retrieval Augmented Generation (RAG). |