TY  - INPR
A1  - Schmülling, Max
A1  - Gützlaff, Joel
A1  - Czupalla, Markus
T1  - A thermal simulation environment for moving objects on the lunar surface
N2  - This paper presents a thermal simulation environment for moving objects on the lunar surface. The goal of the thermal simulation environment is to enable the reliable prediction of the temperature development of a given object on the lunar surface by providing the respective heat fluxes for a mission on a given travel path. The user can import any object geometry and freely define the path that the object should travel. Using the path of the object, the relevant lunar surface geometry is imported from a digital elevation model. The relevant parts of the lunar surface are determined based on distance to the defined path. A thermal model of these surface sections is generated, consisting of a porous layer on top and a denser layer below. The object is moved across the lunar surface, and its inclination is adapted depending on the slope of the terrain below it. Finally, a transient thermal analysis of the object and its environment is performed at several positions on its path and the results are visualized. The paper introduces details on the thermal modeling of the lunar surface, as well as its verification. Furthermore, the structure of the created software is presented. The robustness of the environment is verified with the help of sensitivity studies and possible improvements are presented.
KW  - Dynamic modeling
KW  - Thermal analysis
KW  - ESATAN-TMS
KW  - Lunar Surface
KW  - Thermal Model
Y1  - 2024
U6  - https://doi.org/10.21203/rs.3.rs-3902363/v1
ER  - 
TY  - INPR
A1  - Bornheim, Tobias
A1  - Grieger, Niklas
A1  - Blaneck, Patrick Gustav
A1  - Bialonski, Stephan
T1  - Preprint: Speaker attribution in German parliamentary debates with QLoRA-adapted large language models
T2  - Journal for Language Technology and Computational Linguistics
N2  - The growing body of political texts opens up new opportunities for rich insights into political dynamics and ideologies but also increases the workload for manual analysis. Automated speaker attribution, which detects who said what to whom in a speech event and is closely related to semantic role labeling, is an important processing step for computational text analysis. We study the potential of the large language model family Llama 2 to automate speaker attribution in German parliamentary debates from 2017-2021. We fine-tune Llama 2 with QLoRA, an efficient training strategy, and observe our approach to achieve competitive performance in the GermEval 2023 Shared Task On Speaker Attribution in German News Articles and Parliamentary Debates. Our results shed light on the capabilities of large language models in automating speaker attribution, revealing a promising avenue for computational analysis of political discourse and the development of semantic role labeling systems.
Y1  - 2023
U6  - https://doi.org/10.48550/arXiv.2309.09902
N1  - Veröffentlichte Version verfügbar unter: https://doi.org/10.21248/jlcl.37.2024.244
ER  -