German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data

1 code implementation • 16 Feb 2024 • Lars Klöser, Mika Beele, Jan-Niklas Schagen, Bodo Kraft

This study pioneers the use of synthetically generated data for training generative models in document-level text simplification of German texts.

Text Simplification

Explaining Relation Classification Models with Semantic Extents

2 code implementations • 4 Aug 2023 • Lars Klöser, Andre Büsgen, Philipp Kohl, Bodo Kraft, Albert Zündorf

We introduce semantic extents, a concept to analyze decision patterns for the relation classification task.

Classification Relation +1

Multi-Attribute Relation Extraction (MARE) -- Simplifying the Application of Relation Extraction

1 code implementation • 17 Nov 2021 • Lars Klöser, Philipp Kohl, Bodo Kraft, Albert Zündorf

Extracting relations with an arbitrary amount of attributes requires complex systems and costly relation-trigger annotations to assist these systems.

Attribute Binary Relation Extraction +3

STAMP 4 NLP -- An Agile Framework for Rapid Quality-Driven NLP Applications Development

no code implementations • 16 Nov 2021 • Philipp Kohl, Oliver Schmidts, Lars Klöser, Henri Werth, Bodo Kraft, Albert Zündorf

The progress in natural language processing (NLP) research over the last years, offers novel business opportunities for companies, as automated user interaction or improved data analysis.