Papers by Melanie Siegel

2 papers
GerDISDETECT: A German Multilabel Dataset for Disinformation Detection (2024.lrec-main)

Copied to clipboard

Challenge: Disinformation datasets are sparse and expensive to train . annotated datasets often have only binary or multiclass labels .
Approach: They propose to use a textual dataset to detect disinformation in German . the dataset contains 39 multilabel classes with 5 top-level categories .
Outcome: The proposed dataset provides comprehensive insights into disinformation in German using a taxonomy guided annotation scheme.
A Preliminary Study of ChatGPT for Spanish E2R Text Adaptation (2024.lrec-main)

Copied to clipboard

Challenge: 16% of the world's population lacks literacy skills, according to the United Nations .
Approach: They propose to use ChatGPT-4 to generate E2R text prompts and a checklist-based manual evaluation to evaluate 10 texts adapted by ChatGPt-4.
Outcome: The proposed model is able to generate written language and adapt to LF in 10 texts.

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