3 citations · 6 across the 5 of their papers we have counts for
5 papers
Profiling German Text Simplification with Interpretable Model-Fingerprints
Lars Klöser, Mika Beele, Bodo Kraft
While Large Language Models (LLMs) produce highly nuanced text simplifications, developers currently lack tools for a holistic, efficient, and reproducible diagnosis of their behav…
German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data
Lars Klöser, Mika Beele, Jan-Niklas Schagen +1
This study pioneers the use of synthetically generated data for training generative models in document-level text simplification of German texts. We demonstrate the effectiveness o…
Explaining Relation Classification Models with Semantic Extents
Lars Klöser, Andre Büsgen, Philipp Kohl +2
In recent years, the development of large pretrained language models, such as BERT and GPT, significantly improved information extraction systems on various tasks, including relati…
Multi-Attribute Relation Extraction (MARE) -- Simplifying the Application of Relation Extraction
Lars Klöser, Philipp Kohl, Bodo Kraft +1
Natural language understanding's relation extraction makes innovative and encouraging novel business concepts possible and facilitates new digitilized decision-making processes. Cu…
STAMP 4 NLP -- An Agile Framework for Rapid Quality-Driven NLP Applications Development
Philipp Kohl, Oliver Schmidts, Lars Klöser +3
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 an…