Melanie Siegel — accepted AI-conference papers

2024

A Preliminary Study of ChatGPT for Spanish E2R Text Adaptation

Margot Madina, Itziar Gonzalez-Dios, Melanie Siegel

COLING 2024main

The process of adapting and creating Easy-to-Read (E2R) texts is very expensive and time-consuming. Due to the success of Large Language Models (LLMs) such as ChatGPT and their ability to generate written language, it is likely to think that such models can help in the adaptation or creation of text…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

GerDISDETECT: A German Multilabel Dataset for Disinformation Detection

Mina Schütz, Daniela Pisoiu, Daria Liakhovets, Alexander Schindler, Melanie Siegel

COLING 2024main

Disinformation has become increasingly relevant in recent years both as a political issue and as object of research. Datasets for training machine learning models, especially for other languages than English, are sparse and the creation costly. Annotated datasets often have only binary or multiclass…

Cited by 4 Source ↗PDF ↗Scholar ↗