@article{SildatkeKarwanniKraftetal.2023, author = {Sildatke, Michael and Karwanni, Hendrik and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {A distributed microservice architecture pattern for the automated generation of information extraction pipelines}, series = {SN Computer Science}, journal = {SN Computer Science}, number = {4, Article number: 833}, publisher = {Springer Singapore}, address = {Singapore}, issn = {2661-8907}, doi = {10.1007/s42979-023-02256-4}, pages = {19 Seiten}, year = {2023}, abstract = {Companies often build their businesses based on product information and therefore try to automate the process of information extraction (IE). Since the information source is usually heterogeneous and non-standardized, classic extract, transform, load techniques reach their limits. Hence, companies must implement the newest findings from research to tackle the challenges of process automation. They require a flexible and robust system that is extendable and ensures the optimal processing of the different document types. This paper provides a distributed microservice architecture pattern that enables the automated generation of IE pipelines. Since their optimal design is individual for each input document, the system ensures the ad-hoc generation of pipelines depending on specific document characteristics at runtime. Furthermore, it introduces the automated quality determination of each available pipeline and controls the integration of new microservices based on their impact on the business value. The introduced system enables fast prototyping of the newest approaches from research and supports companies in automating their IE processes. Based on the automated quality determination, it ensures that the generated pipelines always meet defined business requirements when they come into productive use.}, language = {en} } @inproceedings{SiebigterothKraftSchmidtsetal.2019, author = {Siebigteroth, Ines and Kraft, Bodo and Schmidts, Oliver and Z{\"u}ndorf, Albert}, title = {A Study on Improving Corpus Creation by Pair Annotation}, series = {Proceedings of the Poster Session of the 2nd Conference on Language, Data and Knowledge (LDK-PS 2019)}, booktitle = {Proceedings of the Poster Session of the 2nd Conference on Language, Data and Knowledge (LDK-PS 2019)}, issn = {1613-0073}, pages = {40 -- 44}, year = {2019}, 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. DeLTA 2023. Communications in Computer and Information Science}, booktitle = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science}, editor = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-39058-6 (Print)}, doi = {978-3-031-39059-3}, 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} } @article{KraftHeerRetkowitz2008, author = {Kraft, Bodo and Heer, Thomas and Retkowitz, Daniel}, title = {Algorithm and Tool for Ontology Integration Based on Graph Rewriting / Heer, Thomas ; Retkowitz, Daniel ; Kraft, Bodo}, series = {Applications of Graph Transformations with Industrial Relevance / Third International Symposium, AGTIVE 2007, Kassel, Germany, October 10-12, 2007, Revised Selected and Invited Papers}, journal = {Applications of Graph Transformations with Industrial Relevance / Third International Symposium, AGTIVE 2007, Kassel, Germany, October 10-12, 2007, Revised Selected and Invited Papers}, isbn = {978-3-540-89019-5}, pages = {577 -- 582}, year = {2008}, language = {en} } @incollection{KraftKohlMeinecke2024, author = {Kraft, Bodo and Kohl, Philipp and Meinecke, Matthias}, title = {Analyse und Nachverfolgung von Projektzielen durch Einsatz von Natural Language Processing}, series = {KI in der Projektwirtschaft : was ver{\"a}ndert sich durch KI im Projektmanagement?}, booktitle = {KI in der Projektwirtschaft : was ver{\"a}ndert sich durch KI im Projektmanagement?}, editor = {Bernert, Christian and Scheurer, Steffen and Wehnes, Harald}, publisher = {UVK Verlag}, isbn = {978-3-3811-1132-9 (Online)}, doi = {10.24053/9783381111329}, pages = {157 -- 167}, year = {2024}, language = {de} } @inproceedings{SildatkeKarwanniKraftetal.2020, author = {Sildatke, Michael and Karwanni, Hendrik and Kraft, Bodo and Schmidts, Oliver and Z{\"u}ndorf, Albert}, title = {Automated Software Quality Monitoring in Research Collaboration Projects}, series = {ICSEW'20: Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops}, booktitle = {ICSEW'20: Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops}, doi = {10.1145/3387940.3391478}, pages = {603 -- 610}, year = {2020}, language = {en} } @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{SchmidtsKraftWinkensetal.2020, author = {Schmidts, Oliver and Kraft, Bodo and Winkens, Marvin and Z{\"u}ndorf, Albert}, title = {Catalog integration of low-quality product data by attribute label ranking}, series = {Proceedings of the 9th International Conference on Data Science, Technology and Applications - Volume 1: DATA}, booktitle = {Proceedings of the 9th International Conference on Data Science, Technology and Applications - Volume 1: DATA}, isbn = {978-989-758-440-4}, doi = {10.5220/0009831000900101}, pages = {90 -- 101}, year = {2020}, language = {en} } @article{Kraft2003, author = {Kraft, Bodo}, title = {Conceptual design mit ArchiCAD 8 : Forschungsprojekt an der RWTH Aachen}, year = {2003}, abstract = {Projektbericht in GraphisoftNews - Architektur und Bauen in einer vernetzten Welt 3/2003 4 Seiten}, subject = {CAD}, language = {de} } @inproceedings{Kraft2004, author = {Kraft, Bodo}, title = {Conceptual design tools for civil engineering}, year = {2004}, abstract = {Applications of Graph Transformations with Industrial Relevance Lecture Notes in Computer Science, 2004, Volume 3062/2004, 434-439, DOI: http://dx.doi.org/10.1007/978-3-540-25959-6_33 This paper gives a brief overview of the tools we have developed to support conceptual design in civil engineering. Based on the UPGRADE framework, two applications, one for the knowledge engineer and another for architects allow to store domain specific knowledge and to use this knowledge during conceptual design. Consistency analyses check the design against the defined knowledge and inform the architect if rules are violated.}, subject = {CAD}, language = {en} }