Enhancing Rhetorical Figure Annotation: An Ontology-Based Web Application with RAG Integration
Ramona K\"uhn, Jelena Mitrovi\'c, Michael Granitzer

TL;DR
This paper introduces a web application that leverages an adapted German rhetorical ontology and Retrieval Augmented Generation (RAG) to facilitate the annotation of rhetorical figures, aiding in NLP tasks like hate speech detection.
Contribution
It presents a novel integration of rhetorical ontologies with RAG in a web tool for annotating German rhetorical figures, addressing data scarcity in non-English languages.
Findings
The web application improves annotation efficiency.
Optimal RAG settings enhance figure identification.
Promising results in using ontologies with RAG for rhetorical analysis.
Abstract
Rhetorical figures play an important role in our communication. They are used to convey subtle, implicit meaning, or to emphasize statements. We notice them in hate speech, fake news, and propaganda. By improving the systems for computational detection of rhetorical figures, we can also improve tasks such as hate speech and fake news detection, sentiment analysis, opinion mining, or argument mining. Unfortunately, there is a lack of annotated data, as well as qualified annotators that would help us build large corpora to train machine learning models for the detection of rhetorical figures. The situation is particularly difficult in languages other than English, and for rhetorical figures other than metaphor, sarcasm, and irony. To overcome this issue, we develop a web application called "Find your Figure" that facilitates the identification and annotation of German rhetorical figures.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSemantic Web and Ontologies · Natural Language Processing Techniques · Advanced Text Analysis Techniques
MethodsAttention Is All You Need · Linear Layer · Multi-Head Attention · Residual Connection · Adam · Layer Normalization · Weight Decay · Softmax · WordPiece · Attention Dropout
