TY - INPR A1 - Bornheim, Tobias A1 - Niklas, Grieger 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 - http://dx.doi.org/10.48550/arXiv.2309.09902 N1 - Veröffentlichte Version verfügbar unter: https://doi.org/10.21248/jlcl.37.2024.244 ER - TY - JOUR A1 - Horstmann, Marie-Therese A1 - Bialonski, Stephan A1 - Noenning, Nina A1 - Mai, Heinke A1 - Prusseit, Jens A1 - Wellmer, Jörg A1 - Hinrichs, Hermann A1 - Lehnertz, Klaus T1 - State dependent properties of epileptic brain networks: Comparative graph–theoretical analyses of simultaneously recorded EEG and MEG JF - Clinical Neurophysiology N2 - Objective To investigate whether functional brain networks of epilepsy patients treated with antiepileptic medication differ from networks of healthy controls even during the seizure-free interval. Methods We applied different rules to construct binary and weighted networks from EEG and MEG data recorded under a resting-state eyes-open and eyes-closed condition from 21 epilepsy patients and 23 healthy controls. The average shortest path length and the clustering coefficient served as global statistical network characteristics. Results Independent on the behavioral condition, epileptic brains exhibited a more regular functional network structure. Similarly, the eyes-closed condition was characterized by a more regular functional network structure in both groups. The amount of network reorganization due to behavioral state changes was similar in both groups. Consistent findings could be achieved for networks derived from EEG but hardly from MEG recordings, and network construction rules had a rather strong impact on our findings. Conclusions Despite the locality of the investigated processes epileptic brain networks differ in their global characteristics from non-epileptic brain networks. Further methodological developments are necessary to improve the characterization of disturbed and normal functional networks. Significance An increased regularity and a diminished modulation capability appear characteristic of epileptic brain networks. Y1 - 2010 U6 - http://dx.doi.org/10.1016/j.clinph.2009.10.013 SN - 1388-2457 VL - 121 IS - 2 SP - 172 EP - 185 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Bialonski, Stephan A1 - Horstmann, Marie-Therese A1 - Lehnertz, Klaus T1 - From brain to earth and climate systems: Small-world interaction networks or not? JF - Chaos: An Interdisciplinary Journal of Nonlinear Science N2 - We consider recent reports on small-world topologies of interaction networks derived from the dynamics of spatially extended systems that are investigated in diverse scientific fields such as neurosciences, geophysics, or meteorology. With numerical simulations that mimic typical experimental situations, we have identified an important constraint when characterizing such networks: indications of a small-world topology can be expected solely due to the spatial sampling of the system along with the commonly used time series analysis based approaches to network characterization. Y1 - 2010 U6 - http://dx.doi.org/10.1063/1.3360561 SN - 1089-7682 VL - 20 IS - 1 PB - AIP Publishing CY - Melville, NY ER - TY - JOUR A1 - Bialonski, Stephan A1 - Wendler, Martin A1 - Lehnertz, Klaus T1 - Unraveling spurious properties of interaction networks with tailored random networks JF - Plos one N2 - We investigate interaction networks that we derive from multivariate time series with methods frequently employed in diverse scientific fields such as biology, quantitative finance, physics, earth and climate sciences, and the neurosciences. Mimicking experimental situations, we generate time series with finite length and varying frequency content but from independent stochastic processes. Using the correlation coefficient and the maximum cross-correlation, we estimate interdependencies between these time series. With clustering coefficient and average shortest path length, we observe unweighted interaction networks, derived via thresholding the values of interdependence, to possess non-trivial topologies as compared to Erdös-Rényi networks, which would indicate small-world characteristics. These topologies reflect the mostly unavoidable finiteness of the data, which limits the reliability of typically used estimators of signal interdependence. We propose random networks that are tailored to the way interaction networks are derived from empirical data. Through an exemplary investigation of multichannel electroencephalographic recordings of epileptic seizures – known for their complex spatial and temporal dynamics – we show that such random networks help to distinguish network properties of interdependence structures related to seizure dynamics from those spuriously induced by the applied methods of analysis. Y1 - 2011 U6 - http://dx.doi.org/10.1371/journal.pone.0022826 VL - 6 IS - 8 PB - Plos CY - San Francisco ER - TY - JOUR A1 - Kuhnert, Marie-Therese A1 - Bialonski, Stephan A1 - Noenning, Nina A1 - Mai, Heinke A1 - Hinrichs, Hermann A1 - Helmstaedter, Christoph A1 - Lehnertz, Klaus T1 - Incidental and intentional learning of verbal episodic material differentially modifies functional brain networks JF - Plos one N2 - Learning- and memory-related processes are thought to result from dynamic interactions in large-scale brain networks that include lateral and mesial structures of the temporal lobes. We investigate the impact of incidental and intentional learning of verbal episodic material on functional brain networks that we derive from scalp-EEG recorded continuously from 33 subjects during a neuropsychological test schedule. Analyzing the networks' global statistical properties we observe that intentional but not incidental learning leads to a significantly increased clustering coefficient, and the average shortest path length remains unaffected. Moreover, network modifications correlate with subsequent recall performance: the more pronounced the modifications of the clustering coefficient, the higher the recall performance. Our findings provide novel insights into the relationship between topological aspects of functional brain networks and higher cognitive functions. Y1 - 2013 U6 - http://dx.doi.org/10.1371/journal.pone.0080273 VL - 8 IS - 11 PB - PLOS CY - San Francisco ER -