Suche

- Das Campus Stüble – gelegen in der Münzgasse in Schlossnähe in der ehemaligen Vögele-Filiale – soll den DHBW-Studierenden die Möglichkeit geben, sich zu treffen. Möglich ist dies nur durch die Unterstützung der Stiftung Pro DHBW Mosbach, die für die Studierenden anmietet. Die feierliche Übergabe im Mai übernahm daher auch Stiftungsgeschäftsführer Gerhard Lauth im Beisein von Sponsoren, Studierenden und Hochschulmitgliedern. Im Juni waren die letzten juristischen und organisatorischen Details zu klären, der Raum ist nun einsatzbereit. Der DHBW-Standort in Bad Mergentheim sei "der erste und einzige, der so eine Einrichtung hat", erklärte Gerhard Lauth. Er merkte an, dass die Zusammenarbeit zwischen Stiftung, Vermieter, Stadt, dem Campus Bad Mergentheim, vor allem den Professoren Enrico Purle und Rainer Jochum als Initiatoren des Projekts, und den Partnerunternehmen ALDI Süd und VS Vereinigte Spezialmöbelfabriken bestens funktioniert hätte – sodass man das Campus Stüble eröffnen könne und den Studierenden in Bad Mergentheim einen lang gehegten Wunsch erfülle. "Studium ist so viel mehr als Wissenserwerb", stellte Prof. Dr. Gabi Jeck-Schlottmann, Rektorin DHBW Mosbach, in ihrer Dankesrede dar, und wandte sich an die anwesenden Studierenden: "Besonders an der DHBW haben Sie eine große Vielfalt an Menschen mit unterschiedlichen Hintergründen – wenn Sie Ihre Erfahrungen und Standpunkte teilen, können sie so viel lernen." Hochschule sei ein Ort der sozialen Begegnung und des sozialen Lernens und dazu brauche es Raum, auch physisch, schloss sich Campusleiterin Prof. Dr. Kim Linsenmayer an. Sie wisse aus eigener Erfahrung, wie sehr Erlebnisse außerhalb der Lehrräume massiv prägen. Bad Mergentheims Oberbürgermeister Udo Glatthaar dankte allen Beteiligten, dass sie das Projekt "Campus Stüble" zur Herzenssache gemacht hätten und machte deutlich: "Ich darf ankündigen, dass das ein Baustein ist, ein Mosaik in der Weiterentwicklung der DHBW vor Ort. Die Stadt bekenne sich zum Ausbau der Dualen Hochschule, meinte er, "da bin ich auch auf Landesebene nicht ruhig.“ Sebastian Behl, Director Warehouse Operations von Aldi Süd Helmstadt, freute sich darüber, an seine Alma Mater zurückzukommen: "Wir haben 2022 unser Engagement vertieft, im Jahrgang 2023 sind 24 ALDI Süd-Studenten hier gestartet, was eine stolze Zahl ist." Netzwerken und Gemeinschaft zu erleben sei wichtig: "Umso schöner ist es, einen solchen Raum zu haben, zu dem wir gerne unseren Beitrag leisten." Steffen Weis, VS-Geschäftsführer erläuterte: "Uns ist wichtig, dass unser soziales Engagement zielgerichtet ist. Wir möchten in der Region und beim Thema Bildung unterstützen", hier falle beides zusammen. Als "Ausstatter der Wissensgesellschaft“ habe man deshalb die komplette Möblierung und mediale Ausstattung des Campus Stüble übernommen. Studierendensprecher Luis Wronski machte darauf aufmerksam, dass er zu Beginn seines Studiums teilweise einsam war: "Es war Winter, regnerisch, kalt, nicht wirklich einladend." Das habe sich schnell durch seine Kommilitoninnen und Kommilitonen geändert. Inzwischen freue er sich, wenn er nach Bad Mergentheim zurückkomme.

- SportsTables: A new Corpus for Semantic Type Detection Authors: Sven Langenecker, Christoph Sturm, Christian Schalles, Carsten Binnig Table corpora such as VizNet or TURL which contain annotated semantic types per column are important to build machine learning models for the task of automatic semantic type detection. However, there is a huge discrepancy between corpora that are used for training and testing since real-world data lakes contain a huge fraction of numerical data which are not present in existing corpora. Hence, in this paper, we introduce a new corpus that contains a much higher proportion of numerical columns than existing corpora. To reflect the distribution in real-world data lakes, our corpus SportsTables has on average approx. 86% numerical columns, posing new challenges to existing semantic type detection models which have mainly targeted non-numerical columns so far. To demonstrate this effect, we show the results of a first study using a state-of-the-art approach for semantic type detection on our new corpus and demonstrate significant performance differences in predicting semantic types for textual and numerical data. https://doi.org/10.18420/BTW2023-68

- Steered Training Data Generation for Learned Semantic Type Detection Authors: Sven Langenecker, Christoph Sturm, Christian Schalles, Carsten Binnig The poster introduces STEER to adapt learned semantic type extraction approaches to a new, unseen data lake. STEER provides a data programming framework for semantic labeling which is used to generate new labeled training data with minimal overhead. At its core, STEER comes with a novel training data generation procedure called Steered-Labeling that can generate high quality training data not only for non-numeric but also for numerical columns. With this generated training data STEER is able to fine-tune existing learned semantic type extraction models. We evaluate our approach on four different data lakes and show that we can significantly improve the performance of two different types of learned models across all data lakes. https://www.dhbw.de/fileadmin/user_upload/Dokumente/Forschung/AI_Transfer_Congress/Proceedings_DHBW_AITC_2023.pdf

- Steered Training Data Generation for Learned Semantic Type Detection Authors: Sven Langenecker, Christoph Sturm, Christian Schalles, Carsten Binnig In this paper, we introduce STEER to adapt learned semantic type extraction approaches to a new, unseen data lake. STEER provides a data programming framework for semantic labeling which is used to generate new labeled training data with minimal overhead. At its core, STEER comes with a novel training data generation procedure called Steered-Labeling that can generate high quality training data not only for non-numeric but also for numerical columns. With this generated training data STEER is able to fine-tune existing learned semantic type extraction models. We evaluate our approach on four different data lakes and show that we can significantly improve the performance of two different types of learned models across all data lakes. https://doi.org/10.1145/3589786

- SportsTables: A New Corpus for Semantic Type Detection (Extended Version) Authors: Sven Langenecker, Christoph Sturm, Christian Schalles, Carsten Binnig Table corpora such as VizNet or TURL which contain annotated semantic types per column are important to build machine learning models for the task of automatic semantic type detection. However, there is a huge discrepancy between corpora and real-world data lakes since they contain a huge fraction of numerical data which are not present in existing corpora. Hence, in this paper, we introduce a new corpus that contains a much higher proportion of numerical columns than existing corpora. To reflect the distribution in real-world data lakes, our corpus SportsTables has on average approx. 86% numerical columns, posing new challenges to existing semantic type detection models which have mainly targeted non-numerical columns so far. To demonstrate this effect, we show in this extended version paper of [ 18 ] the results of an extensive study using four different state-of-the-art approaches for semantic type detection on our new corpus. Overall, the results demonstrate significant performance differences in predicting semantic types for textual and numerical data. https://doi.org/10.1007/s13222-023-00457-y

- Pythagoras: Semantic Type Detection of Numerical Data Using Graph Neural Networks Authors: Sven Langenecker, Christoph Sturm, Christian Schalles, Carsten Binnig Detecting semantic types of table columns is a crucial task to enable dataset discovery in data lakes. However, prior semantic type detection approaches have primarily focused on non-numeric data despite the fact that numeric data play an essential role in many enterprise data lakes. Therefore, typically, existing models are rather inadequate when applied to data lakes that contain a high proportion of numerical data. In this paper, we introduce Pythagoras , our new learned semantic type detection approach specially designed to support numerical data along with non-numerical data. Pythagoras uses a graph neural network based on a new graph representation of tables to predict the semantic types for numerical data with high accuracy. In our initial experiments, we thus achieve F1-Scores of 0.829 (support-weighted) and 0.790 (macro), respectively, exceeding the state-of-the-art performance significantly. https://ceur-ws.org/Vol-3630/LWDA2023-paper13.pdf

- Pythagoras: Semantic Type Detection of Numerical Data in Enterprise Data Lakes Authors: Sven Langenecker, Christoph Sturm, Christian Schalles, Carsten Binnig Detecting semantic types of table columns is a crucial task to enable dataset discovery in data lakes. However, prior semantic type detection approaches have primarily focused on non-numerical data despite the fact that numerical data play an essential role in many real-world enterprise data lakes. Therefore, existing models are typically rather inadequate when applied to data lakes that contain a high proportion of numerical data. In this paper, we introduce Pythagoras, our new learned semantic type detection approach specially designed to support numerical along with non-numerical data. Pythagoras uses a GNN in combination with a novel graph representation of tables to predict the semantic types for numerical data with high accuracy. In our experiments, we compare Pythagoras against five state-of-the-art approaches using two different datasets and show that our model significantly outperforms these baselines on numerical data. In comparison to the best existing approach, we achieve F1-Score increases of around +22%, which sets new benchmarks. https://dx.doi.org/10.48786/edbt.2024.62