@inproceedings{SchmidtsKraftWinkensetal.2021, author = {Schmidts, Oliver and Kraft, Bodo and Winkens, Marvin and Z{\"u}ndorf, Albert}, title = {Catalog integration of heterogeneous and volatile product data}, series = {DATA 2020: Data Management Technologies and Applications}, booktitle = {DATA 2020: Data Management Technologies and Applications}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-83013-7}, doi = {10.1007/978-3-030-83014-4_7}, pages = {134 -- 153}, year = {2021}, abstract = {The integration of frequently changing, volatile product data from different manufacturers into a single catalog is a significant challenge for small and medium-sized e-commerce companies. They rely on timely integrating product data to present them aggregated in an online shop without knowing format specifications, concept understanding of manufacturers, and data quality. Furthermore, format, concepts, and data quality may change at any time. Consequently, integrating product catalogs into a single standardized catalog is often a laborious manual task. Current strategies to streamline or automate catalog integration use techniques based on machine learning, word vectorization, or semantic similarity. However, most approaches struggle with low-quality or real-world data. We propose Attribute Label Ranking (ALR) as a recommendation engine to simplify the integration process of previously unknown, proprietary tabular format into a standardized catalog for practitioners. We evaluate ALR by focusing on the impact of different neural network architectures, language features, and semantic similarity. Additionally, we consider metrics for industrial application and present the impact of ALR in production and its limitations.}, language = {en} } @inproceedings{GoldmannBraunsteinHeinrichetal.2015, author = {Goldmann, Jan-Peter and Braunstein, Bjoern and Heinrich, Kai and Sanno, Maximilian and St{\"a}udle, Benjamin and Ritzdorf, Wolfgang and Br{\"u}ggemann, Gert-Peter and Albracht, Kirsten}, title = {Joint work of the take-off leg during elite high jump}, series = {Proceedings of the 33th International Conference on Biomechanics in Sports (ISBS)}, booktitle = {Proceedings of the 33th International Conference on Biomechanics in Sports (ISBS)}, pages = {3 S.}, year = {2015}, language = {en} } @inproceedings{DroszezSannoGoldmannetal.2016, author = {Droszez, Anna and Sanno, Maximilian and Goldmann, Jan-Peter and Albracht, Kirsten and Br{\"u}ggemann, Gerd-Peter and Braunstein, Bjoern}, title = {Differences between take-off behavior during vertical jumps and two artistic elements}, series = {34th International Conference of Biomechanics in Sport, Tsukuba, Japan, July 18-22, 2016}, booktitle = {34th International Conference of Biomechanics in Sport, Tsukuba, Japan, July 18-22, 2016}, issn = {1999-4168}, pages = {577 -- 580}, year = {2016}, language = {en} } @inproceedings{AbelBoninAlbrachtetal.2010, author = {Abel, Thomas and Bonin, Dominik and Albracht, Kirsten and Zeller, Sebastian and Br{\"u}ggemann, Gert-Peter and Burkett, Brendan and Str{\"u}der, Heiko K.}, title = {Kinematic profile of the elite handcyclist}, series = {28th International Conference on Biomechanics in Sports, Marquette, Michigan, USA, July 19 - 23, 2010}, booktitle = {28th International Conference on Biomechanics in Sports, Marquette, Michigan, USA, July 19 - 23, 2010}, issn = {1999-4168}, pages = {140 -- 141}, year = {2010}, language = {en} } @inproceedings{BraunsteinGoldmannAlbrachtetal.2013, author = {Braunstein, Bjoern and Goldmann, Jan-Peter and Albracht, Kirsten and Sanno, Maximilian and Willwacher, Steffen and Heinrich, Kai and Herrmann, Volker and Br{\"u}ggemann, Gert-Peter}, title = {Joint specific contribution of mechanical power and work during acceleration and top speed in elite sprinters}, series = {31 International Conference on Biomechanics in Sports, Taipei, Taiwan, July 07 - July 22, 2013}, booktitle = {31 International Conference on Biomechanics in Sports, Taipei, Taiwan, July 07 - July 22, 2013}, issn = {1999-4168}, year = {2013}, language = {en} } @inproceedings{KolditzAlbrachtFasseetal.2015, author = {Kolditz, Melanie and Albracht, Kirsten and Fasse, Alessandro and Albin, Thivaharan and Br{\"u}ggemann, Gert-Peter and Abel, Dirk}, title = {Evaluation of an industrial robot as a leg press training device}, series = {XV International Symposium on Computer Simulation in Biomechanics July 9th - 11th 2015, Edinburgh, UK}, booktitle = {XV International Symposium on Computer Simulation in Biomechanics July 9th - 11th 2015, Edinburgh, UK}, pages = {41 -- 42}, year = {2015}, language = {en} } @inproceedings{KolditzAlbinFasseetal.2015, author = {Kolditz, Melanie and Albin, Thivaharan and Fasse, Alessandro and Br{\"u}ggemann, Gert-Peter and Abel, Dirk and Albracht, Kirsten}, title = {Simulative Analysis of Joint Loading During Leg Press Exercise for Control Applications}, series = {IFAC-PapersOnLine}, volume = {48}, booktitle = {IFAC-PapersOnLine}, number = {20}, doi = {10.1016/j.ifacol.2015.10.179}, pages = {435 -- 440}, year = {2015}, language = {en} } @inproceedings{BehbahaniRibleMoulinecetal.2015, author = {Behbahani, Mehdi and Rible, Sebastian and Moulinec, Charles and Fournier, Yvan and Nicolai, Mike and Crosetto, Paolo}, title = {Simulation of the FDA Centrifugal Blood Pump Using High Performance Computing}, series = {World Academy of Science, Engineering and Technology International Journal of Mechanical and Mechatronics Engineering}, volume = {9}, booktitle = {World Academy of Science, Engineering and Technology International Journal of Mechanical and Mechatronics Engineering}, number = {5}, year = {2015}, language = {en} } @inproceedings{BuesgenKloeserKohletal.2023, author = {B{\"u}sgen, Andr{\´e} and Kl{\"o}ser, Lars and Kohl, Philipp and Schmidts, Oliver and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {From cracked accounts to fake IDs: user profiling on German telegram black market channels}, series = {Data Management Technologies and Applications}, booktitle = {Data Management Technologies and Applications}, editor = {Cuzzocrea, Alfredo and Gusikhin, Oleg and Hammoudi, Slimane and Quix, Christoph}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-37889-8 (Print)}, doi = {10.1007/978-3-031-37890-4_9}, pages = {176 -- 202}, year = {2023}, abstract = {Messenger apps like WhatsApp and Telegram are frequently used for everyday communication, but they can also be utilized as a platform for illegal activity. Telegram allows public groups with up to 200.000 participants. Criminals use these public groups for trading illegal commodities and services, which becomes a concern for law enforcement agencies, who manually monitor suspicious activity in these chat rooms. This research demonstrates how natural language processing (NLP) can assist in analyzing these chat rooms, providing an explorative overview of the domain and facilitating purposeful analyses of user behavior. We provide a publicly available corpus of annotated text messages with entities and relations from four self-proclaimed black market chat rooms. Our pipeline approach aggregates the extracted product attributes from user messages to profiles and uses these with their sold products as features for clustering. The extracted structured information is the foundation for further data exploration, such as identifying the top vendors or fine-granular price analyses. Our evaluation shows that pretrained word vectors perform better for unsupervised clustering than state-of-the-art transformer models, while the latter is still superior for sequence labeling.}, language = {en} } @inproceedings{KohlFreyerKraemeretal.2023, author = {Kohl, Philipp and Freyer, Nils and Kr{\"a}mer, Yoka and Werth, Henri and Wolf, Steffen and Kraft, Bodo and Meinecke, Matthias and Z{\"u}ndorf, Albert}, title = {ALE: a simulation-based active learning evaluation framework for the parameter-driven comparison of query strategies for NLP}, series = {Deep Learning Theory and Applications}, booktitle = {Deep Learning Theory and Applications}, editor = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-39058-6 (Print)}, doi = {10.1007/978-3-031-39059-3_16}, pages = {235 -- 253}, year = {2023}, abstract = {Supervised machine learning and deep learning require a large amount of labeled data, which data scientists obtain in a manual, and time-consuming annotation process. To mitigate this challenge, Active Learning (AL) proposes promising data points to annotators they annotate next instead of a subsequent or random sample. This method is supposed to save annotation effort while maintaining model performance. However, practitioners face many AL strategies for different tasks and need an empirical basis to choose between them. Surveys categorize AL strategies into taxonomies without performance indications. Presentations of novel AL strategies compare the performance to a small subset of strategies. Our contribution addresses the empirical basis by introducing a reproducible active learning evaluation (ALE) framework for the comparative evaluation of AL strategies in NLP. The framework allows the implementation of AL strategies with low effort and a fair data-driven comparison through defining and tracking experiment parameters (e.g., initial dataset size, number of data points per query step, and the budget). ALE helps practitioners to make more informed decisions, and researchers can focus on developing new, effective AL strategies and deriving best practices for specific use cases. With best practices, practitioners can lower their annotation costs. We present a case study to illustrate how to use the framework.}, language = {en} }