@article{BornheimGriegerBlanecketal.2024, author = {Bornheim, Tobias and Grieger, Niklas and Blaneck, Patrick Gustav and Bialonski, Stephan}, title = {Speaker Attribution in German Parliamentary Debates with QLoRA-adapted Large Language Models}, series = {Journal for language technology and computational linguistics : JLCL}, volume = {37}, journal = {Journal for language technology and computational linguistics : JLCL}, number = {1}, publisher = {Gesellschaft f{\"u}r Sprachtechnologie und Computerlinguistik}, address = {Regensburg}, issn = {2190-6858}, doi = {10.21248/jlcl.37.2024.244}, pages = {13 Seiten}, year = {2024}, abstract = {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analysis of political discourse and the development of semantic role labeling systems.}, language = {en} } @unpublished{GriegerMehrkanoonBialonski2024, author = {Grieger, Niklas and Mehrkanoon, Siamak and Bialonski, Stephan}, title = {Preprint: Data-efficient sleep staging with synthetic time series pretraining}, series = {arXiv}, journal = {arXiv}, pages = {10 Seiten}, year = {2024}, abstract = {Analyzing electroencephalographic (EEG) time series can be challenging, especially with deep neural networks, due to the large variability among human subjects and often small datasets. To address these challenges, various strategies, such as self-supervised learning, have been suggested, but they typically rely on extensive empirical datasets. Inspired by recent advances in computer vision, we propose a pretraining task termed "frequency pretraining" to pretrain a neural network for sleep staging by predicting the frequency content of randomly generated synthetic time series. Our experiments demonstrate that our method surpasses fully supervised learning in scenarios with limited data and few subjects, and matches its performance in regimes with many subjects. Furthermore, our results underline the relevance of frequency information for sleep stage scoring, while also demonstrating that deep neural networks utilize information beyond frequencies to enhance sleep staging performance, which is consistent with previous research. We anticipate that our approach will be advantageous across a broad spectrum of applications where EEG data is limited or derived from a small number of subjects, including the domain of brain-computer interfaces.}, language = {en} } @inproceedings{BlaneckBornheimGriegeretal.2022, author = {Blaneck, Patrick Gustav and Bornheim, Tobias and Grieger, Niklas and Bialonski, Stephan}, title = {Automatic readability assessment of german sentences with transformer ensembles}, series = {Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text}, booktitle = {Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text}, publisher = {Association for Computational Linguistics}, address = {Potsdam}, doi = {10.48550/arXiv.2209.04299}, pages = {57 -- 62}, year = {2022}, abstract = {Reliable methods for automatic readability assessment have the potential to impact a variety of fields, ranging from machine translation to self-informed learning. Recently, large language models for the German language (such as GBERT and GPT-2-Wechsel) have become available, allowing to develop Deep Learning based approaches that promise to further improve automatic readability assessment. In this contribution, we studied the ability of ensembles of fine-tuned GBERT and GPT-2-Wechsel models to reliably predict the readability of German sentences. We combined these models with linguistic features and investigated the dependence of prediction performance on ensemble size and composition. Mixed ensembles of GBERT and GPT-2-Wechsel performed better than ensembles of the same size consisting of only GBERT or GPT-2-Wechsel models. Our models were evaluated in the GermEval 2022 Shared Task on Text Complexity Assessment on data of German sentences. On out-of-sample data, our best ensemble achieved a root mean squared error of 0:435.}, language = {en} } @article{GriegerSchwabedalWendeletal.2021, author = {Grieger, Niklas and Schwabedal, Justus T. C. and Wendel, Stefanie and Ritze, Yvonne and Bialonski, Stephan}, title = {Automated scoring of pre-REM sleep in mice with deep learning}, series = {Scientific Reports}, volume = {11}, journal = {Scientific Reports}, number = {Art. 12245}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {10.1038/s41598-021-91286-0}, year = {2021}, abstract = {Reliable automation of the labor-intensive manual task of scoring animal sleep can facilitate the analysis of long-term sleep studies. In recent years, deep-learning-based systems, which learn optimal features from the data, increased scoring accuracies for the classical sleep stages of Wake, REM, and Non-REM. Meanwhile, it has been recognized that the statistics of transitional stages such as pre-REM, found between Non-REM and REM, may hold additional insight into the physiology of sleep and are now under vivid investigation. We propose a classification system based on a simple neural network architecture that scores the classical stages as well as pre-REM sleep in mice. When restricted to the classical stages, the optimized network showed state-of-the-art classification performance with an out-of-sample F1 score of 0.95 in male C57BL/6J mice. When unrestricted, the network showed lower F1 scores on pre-REM (0.5) compared to the classical stages. The result is comparable to previous attempts to score transitional stages in other species such as transition sleep in rats or N1 sleep in humans. Nevertheless, we observed that the sequence of predictions including pre-REM typically transitioned from Non-REM to REM reflecting sleep dynamics observed by human scorers. Our findings provide further evidence for the difficulty of scoring transitional sleep stages, likely because such stages of sleep are under-represented in typical data sets or show large inter-scorer variability. We further provide our source code and an online platform to run predictions with our trained network.}, language = {en} } @inproceedings{BornheimGriegerBialonski2021, author = {Bornheim, Tobias and Grieger, Niklas and Bialonski, Stephan}, title = {FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning}, series = {Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments : 17th Conference on Natural Language Processing KONVENS 2021}, booktitle = {Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments : 17th Conference on Natural Language Processing KONVENS 2021}, publisher = {Heinrich Heine University}, address = {D{\"u}sseldorf}, doi = {10.48415/2021/fhw5-x128}, pages = {105 -- 111}, year = {2021}, language = {en} }