Papers by Ramona Kühn

3 papers
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).

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations