@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{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{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{SchreiberKraftZuendorf2016, author = {Schreiber, Marc and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Cost-efficient quality assurance of natural language processing tools through continuous monitoring with continuous integration}, series = {3rd International Workshop on Software Engineering Research and Industrial Practice}, booktitle = {3rd International Workshop on Software Engineering Research and Industrial Practice}, doi = {10.1145/2897022.2897029}, pages = {46 -- 52}, year = {2016}, language = {en} } @inproceedings{SchreiberKraftZuendorf2017, author = {Schreiber, Marc and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Metrics Driven Research Collaboration: Focusing on Common Project Goals Continuously}, series = {39th International Conference on Software Engineering, May 20-28, 2017 - Buenos Aires, Argentina}, booktitle = {39th International Conference on Software Engineering, May 20-28, 2017 - Buenos Aires, Argentina}, pages = {8 Seiten}, year = {2017}, abstract = {Research collaborations provide opportunities for both practitioners and researchers: practitioners need solutions for difficult business challenges and researchers are looking for hard problems to solve and publish. Nevertheless, research collaborations carry the risk that practitioners focus on quick solutions too much and that researchers tackle theoretical problems, resulting in products which do not fulfill the project requirements. In this paper we introduce an approach extending the ideas of agile and lean software development. It helps practitioners and researchers keep track of their common research collaboration goal: a scientifically enriched software product which fulfills the needs of the practitioner's business model. This approach gives first-class status to application-oriented metrics that measure progress and success of a research collaboration continuously. Those metrics are derived from the collaboration requirements and help to focus on a commonly defined goal. An appropriate tool set evaluates and visualizes those metrics with minimal effort, and all participants will be pushed to focus on their tasks with appropriate effort. Thus project status, challenges and progress are transparent to all research collaboration members at any time.}, language = {en} } @inproceedings{SchreiberKraftZuendorf2017, author = {Schreiber, Marc and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Metrics driven research collaboration: focusing on common project goals continuously}, series = {Proceedings : 2017 IEEE/ACM 4th International Workshop on Software Engineering Research and Industrial Practice : SER\&IP 2017 : 21 May 2017 Buenos Aires, Argentina}, booktitle = {Proceedings : 2017 IEEE/ACM 4th International Workshop on Software Engineering Research and Industrial Practice : SER\&IP 2017 : 21 May 2017 Buenos Aires, Argentina}, editor = {Bilof, Randall}, publisher = {IEEE Press}, address = {Piscataway, NJ}, isbn = {978-1-5386-2797-6}, doi = {10.1109/SER-IP.2017..6}, pages = {41 -- 47}, year = {2017}, language = {en} } @inproceedings{SchreiberKraftZuendorf2018, author = {Schreiber, Marc and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {NLP Lean Programming Framework: Developing NLP Applications More Effectively}, series = {Proceedings of NAACL-HLT 2018: Demonstrations, New Orleans, Louisiana, June 2 - 4, 2018}, booktitle = {Proceedings of NAACL-HLT 2018: Demonstrations, New Orleans, Louisiana, June 2 - 4, 2018}, doi = {10.18653/v1/N18-5001 }, pages = {5 Seiten}, year = {2018}, abstract = {This paper presents NLP Lean Programming framework (NLPf), a new framework for creating custom natural language processing (NLP) models and pipelines by utilizing common software development build systems. This approach allows developers to train and integrate domain-specific NLP pipelines into their applications seamlessly. Additionally, NLPf provides an annotation tool which improves the annotation process significantly by providing a well-designed GUI and sophisticated way of using input devices. Due to NLPf's properties developers and domain experts are able to build domain-specific NLP applications more efficiently. NLPf is Opensource software and available at https:// gitlab.com/schrieveslaach/NLPf.}, language = {en} } @inproceedings{SchreiberHirtbachKraftetal.2013, author = {Schreiber, Marc and Hirtbach, Stefan and Kraft, Bodo and Steinmetzler, Andreas}, title = {Software in the city: visual guidance through large scale software projects}, series = {Software Engineering 2013 : Fachtagung des GI-Fachbereichs Softwaretechnik, 26. Februar-1. M{\"a}rz 2013 in Aachen. (GI-Edition ; 213)}, booktitle = {Software Engineering 2013 : Fachtagung des GI-Fachbereichs Softwaretechnik, 26. Februar-1. M{\"a}rz 2013 in Aachen. (GI-Edition ; 213)}, editor = {Kowalewski, Stefan}, publisher = {Ges. f{\"u}r Informatik}, address = {Bonn}, isbn = {978-3-88579-607-7 ; 978-3-88579-609-1}, pages = {213 -- 224}, year = {2013}, language = {en} } @article{SchreiberBarkschatKraftetal.2015, author = {Schreiber, Marc and Barkschat, Kai and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Quick Pad Tagger : An Efficient Graphical User Interface for Building Annotated Corpora with Multiple Annotation Layers}, series = {Computer Science \& Information Technology (CS \& IT)}, volume = {5}, journal = {Computer Science \& Information Technology (CS \& IT)}, number = {4}, publisher = {Academy \& Industry Research Collaboration Center (AIRCC)}, isbn = {978-1-921987-32-8}, issn = {2231 - 5403}, doi = {10.5121/csit.2015.50413}, pages = {131 -- 143}, year = {2015}, language = {en} } @inproceedings{SchreiberBarkschatKraft2014, author = {Schreiber, Marc and Barkschat, Kai and Kraft, Bodo}, title = {Using Continuous Integration to organize and monitor the annotation process of domain specific corpora}, series = {5th International Conference on Information and Communication Systems (ICICS) : 1-3 April 2014, Irbid, Jordanien}, booktitle = {5th International Conference on Information and Communication Systems (ICICS) : 1-3 April 2014, Irbid, Jordanien}, organization = {International Conference on Information and Communication Systems <5, 2014, Irbid, Jordanien>}, isbn = {978-1-4799-3022-7}, doi = {10.1109/IACS.2014.6841958}, pages = {1 -- 6}, year = {2014}, 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} } @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{SchmidtsKraftSiebigterothetal.2019, author = {Schmidts, Oliver and Kraft, Bodo and Siebigteroth, Ines and Z{\"u}ndorf, Albert}, title = {Schema Matching with Frequent Changes on Semi-Structured Input Files: A Machine Learning Approach on Biological Product Data}, series = {Proceedings of the 21st International Conference on Enterprise Information Systems - Volume 1: ICEIS}, booktitle = {Proceedings of the 21st International Conference on Enterprise Information Systems - Volume 1: ICEIS}, isbn = {978-989-758-372-8}, doi = {10.5220/0007723602080215}, pages = {208 -- 215}, year = {2019}, language = {en} } @inproceedings{SchmidtsKraftSchreiberetal.2018, author = {Schmidts, Oliver and Kraft, Bodo and Schreiber, Marc and Z{\"u}ndorf, Albert}, title = {Continuously evaluated research projects in collaborative decoupled environments}, series = {2018 ACM/IEEE 5th International Workshop on Software Engineering Research and Industrial PracticePractice, May 29, 2018, Gothenburg, Sweden : SER\&IP' 18}, booktitle = {2018 ACM/IEEE 5th International Workshop on Software Engineering Research and Industrial PracticePractice, May 29, 2018, Gothenburg, Sweden : SER\&IP' 18}, publisher = {ACM}, address = {New York, NY}, pages = {1 -- 9}, year = {2018}, abstract = {Often, research results from collaboration projects are not transferred into productive environments even though approaches are proven to work in demonstration prototypes. These demonstration prototypes are usually too fragile and error-prone to be transferred easily into productive environments. A lot of additional work is required. Inspired by the idea of an incremental delivery process, we introduce an architecture pattern, which combines the approach of Metrics Driven Research Collaboration with microservices for the ease of integration. It enables keeping track of project goals over the course of the collaboration while every party may focus on their expert skills: researchers may focus on complex algorithms, practitioners may focus on their business goals. Through the simplified integration (intermediate) research results can be introduced into a productive environment which enables getting an early user feedback and allows for the early evaluation of different approaches. The practitioners' business model benefits throughout the full project duration.}, language = {en} } @inproceedings{SchmidtsBoltesKraftetal.2017, author = {Schmidts, Oliver and Boltes, Maik and Kraft, Bodo and Schreiber, Marc}, title = {Multi-pedestrian tracking by moving Bluetooth-LE beacons and stationary receivers}, series = {2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 18-21 September 2017, Sapporo, Japan}, booktitle = {2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 18-21 September 2017, Sapporo, Japan}, pages = {1 -- 4}, year = {2017}, language = {en} } @misc{NobisrathZuendorfGeorgeetal.2017, author = {Nobisrath, Ulrich and Z{\"u}ndorf, Albert and George, Tobias and Ruben, Jubeh and Kraft, Bodo}, title = {Software Stories Guide}, pages = {21}, year = {2017}, abstract = {Software Stories are a simple graphical notation for requirements analysis and design in agile software projects. Software Stories are based on example scenarios. Example scenarios facilitate the communication between lay people or domain experts and software experts.}, language = {en} } @techreport{NaglKraft2004, author = {Nagl, Manfred and Kraft, Bodo}, title = {Graphbasierte Werkzeuge zur Unterst{\"u}tzung des konzeptuellen Geb{\"a}ude-Entwurfs : Bericht {\"u}ber den 2. F{\"o}rderzeitraum des Schwerpunktprogramms : DFG-Schwerpunktprogramm 1103 : Vernetzt-kooperative Planungsprozesse im Konstruktiven Ingenieurbau. - Auch unter dem Titel: Neue Software-Werkzeuge zur Unterst{\"u}tzung des konzeptuellen Geb{\"a}udeentwurfs}, year = {2004}, abstract = {Der konstruktive Entwurf wird in derzeitigen CAD-Systemen gut unterst{\"u}tzt, nicht aber der konzeptuelle Geb{\"a}ude-Entwurf. Dieser abstrahiert von konstruktiven Elementen wie Linie, Wand oder Decke, um auf die Konzepte, d.h. die eigentlichen Funktionen, heraus zu arbeiten. Diese abstraktere, funktionale Sichtweise auf ein Geb{\"a}ude ist w{\"a}hrend der fr{\"u}hen Entwurfsphase essentiell, um Struktur und Organisation des gesamten Geb{\"a}udes zu erfassen. Bereits in dieser Phase muss Fachwissen (z. B. rechtliche, {\"o}konomische und technische Bestimmungen) ber{\"u}cksichtigt werden. Im Rahmen des vorliegenden Projekts werden Software-Werkzeuge integriert in industrielle CAD-Systeme entwickelt, die den konzeptuellen Geb{\"a}ude-Entwurf erm{\"o}glichen und diesen gegen Fachwissen pr{\"u}fen. Das Projekt ist in zwei Teile gegliedert. Im Top-Down-Ansatz werden Datenstrukturen und Methoden zur Strukturierung, Repr{\"a}sentation und Evaluation von geb{\"a}udespezifischem Fachwissen erarbeitet. Dieser Teil baut auf den graphbasierten Werkzeugen PROGRES und UPGRADE des Lehrstuhls auf. Der Bottom-Up-Ansatz ist industriell orientiert und hat zum Ziel, das kommerzielle CAD-System ArchiCAD zu erweitern. Hierbei soll der fr{\"u}he, konzeptuelle Geb{\"a}ude-Entwurf in einem CAD-System erm{\"o}glicht werden. Der Entwurf kann dar{\"u}ber hinaus gegen das definierte Fachwissen gepr{\"u}ft werden. Im Rahmen des graphbasierten Top-Down-Ansatzes wurde zun{\"a}chst eine neue Spezifikationsmethode f{\"u}r die Sprache PROGRES entwickelt. Das PROGRES-System erlaubt die Spezifikation von Werkzeugen in deklarativer Form. {\"U}blicherweise wird dom{\"a}nenspezifisches Fachwissen in der PROGRES-Spezifikation codiert, das daraus generierte visuelle Werkzeug stellt dann die entsprechende Funktionalit{\"a}t zur Verf{\"u}gung. Mit dieser Methode sind am Lehrstuhl f{\"u}r Informatik III Werkzeuge f{\"u}r verschie-dene Anwendungsdom{\"a}nen entstanden. In unserem Fall versetzen wir einen Dom{\"a}nen-Experten, z. B. einen erfahrenen Architekten, in die Lage, Fachwissen zur Laufzeit einzugeben, dieses zu evaluieren, abzu{\"a}ndern oder zu erg{\"a}nzen. Im Rahmen der bisherigen Arbeit wurde dazu eine parametrisierte PROGRES-Spezifikation und zwei darauf aufbauende Werkzeuge entwickelt, welche die dynamische Eingabe von geb{\"a}ude-technisch relevantem Fachwissen erlauben und einen graphbasierten, konzeptuellen Geb{\"a}ude-Entwurf erm{\"o}glichen. In diesem konzeptuellen Geb{\"a}ude-Entwurf wird von Raumgr{\"o}ßen und Positionen abstrahiert, um die funktionale Struktur eines Geb{\"a}udes zu beschreiben. Das Fachwissen kann von einem Architekten visuell definiert werden. Es k{\"o}nnen semantische Einheiten, im einfachsten Fall R{\"a}ume, nach verschiedenen Kriterien kategorisiert und klassifiziert werden. Mit Hilfe von Attributen und Relationen k{\"o}nnen die semantischen Einheiten pr{\"a}ziser beschrieben und in Beziehung zueinander gesetzt werden. Die in PROGRES spezifizierten Konsistenz-Analysen erlauben die Pr{\"u}fung eines graphbasierten konzeptuellen Geb{\"a}ude-Entwurfs gegen das dynamisch eingef{\"u}gte Fachwissen. Im zweiten Teil des Forschungsprojekts, dem Bottom-Up-Ansatz, wird das CAD-System ArchiCAD erweitert, um den integrierten konzeptuellen Geb{\"a}ude-Entwurf zu erm{\"o}glichen. Der Architekt erh{\"a}lt dazu neue Entwurfselemente, die Raumobjekte, welche die relevanten semantischen Einheiten w{\"a}hrend der fr{\"u}hen Entwurfsphase repr{\"a}sentieren. Mit Hilfe der Raumobjekte kann der Architekt in ArchiCAD den Grundriss und das Raumprogramm eines Geb{\"a}udes entwerfen, ohne von konstruktiven Details in seiner Kreativit{\"a}t eingeschr{\"a}nkt zu werden. Die Arbeitsweise mit Raumobjekten entspricht dem informellen konzeptuellen Entwurf auf einer Papierskizze und ist daher f{\"u}r den Architekten intuitiv und einfach zu verwenden. Durch die Integration in ArchiCAD ergibt sich eine weitere Unterst{\"u}tzung: Das im Top-Down-Ansatz spezifizierte Fach-wissen wird verwendet, um den konzeptuellen Geb{\"a}ude-Entwurf des Architekten auf Regelverletzungen zu {\"u}berpr{\"u}fen. Entwurfsfehler werden angezeigt. Zum Abschluss des konzeptuellen Geb{\"a}ude-Entwurfs mit Raumobjekten wird durch ein weiteres neu entwickeltes Werkzeug eine initiale Wandstruktur automatisch erzeugt, die als Grundlage f{\"u}r die folgenden konstruktiven Entwurfsphasen dient. Alle beschriebenen Erwei-terungen sind in ArchiCAD integriert, sie sind f{\"u}r den Architekten daher leicht zu erlernen und einfach zu bedienen.}, subject = {CAD}, language = {de} } @inproceedings{KraftZoell2014, author = {Kraft, Bodo and Z{\"o}ll, Axel}, title = {Von der Langstrecke zum Sprint - Agile Methoden in traditionellen Unternehmen}, series = {Projektmanagement und Vorgehensmodelle 2014 : soziale Aspekte und Standardisierung}, booktitle = {Projektmanagement und Vorgehensmodelle 2014 : soziale Aspekte und Standardisierung}, editor = {Engstler, Martin}, publisher = {Gesellschaft f{\"u}r Informatik}, address = {Bonn}, organization = {FH Aachen, University of Applied Sciences}, isbn = {978-3-88579-630-5}, pages = {35 -- 46}, year = {2014}, language = {de} } @inproceedings{KraftWilhelms2005, author = {Kraft, Bodo and Wilhelms, Nils}, title = {Visual Knowledge Specification for Conceptual Design}, year = {2005}, abstract = {Proc. of the 2005 ASCE Intl. Conf. on Computing in Civil Engineering (ICCC 2005) eds. L. Soibelman und F. Pena-Mora, Seite 1-14, ASCE (CD-ROM), Cancun, Mexico, 2005 Current CAD tools are not able to support the fundamental conceptual design phase, and none of them provides consistency analyses of sketches produced by architects. To give architects a greater support at the conceptual design phase, we develop a CAD tool for conceptual design and a knowledge specification tool allowing the definition of conceptually relevant knowledge. The knowledge is specific to one class of buildings and can be reused. Based on a dynamic knowledge model, different types of design rules formalize the knowledge in a graph-based realization. An expressive visual language provides a user-friendly, human readable representation. Finally, consistency analyses enable conceptual designs to be checked against this defined knowledge. In this paper we concentrate on the knowledge specification part of our project.}, subject = {CAD}, language = {en} } @inproceedings{KraftWilhelms2004, author = {Kraft, Bodo and Wilhelms, N.}, title = {Interactive distributed knowledge support for conceptual building design}, isbn = {3-86068-213-X}, year = {2004}, abstract = {In: Net-distributed Co-operation : Xth International Conference on Computing in Civil and Building Engineering, Weimar, June 02 - 04, 2004 ; proceedings / [ed. by Karl Beuke ...] . - Weimar: Bauhaus-Univ. Weimar 2004. - 1. Aufl. . Seite 1-14 ISBN 3-86068-213-X International Conference on Computing in Civil and Building Engineering <10, 2004, Weimar> Summary In our project, we develop new tools for the conceptual design phase. During conceptual design, the coarse functionality and organization of a building is more important than a detailed worked out construction. We identify two roles, first the knowledge engineer who is responsible for knowledge definition and maintenance; second the architect who elaborates the conceptual de-sign. The tool for the knowledge engineer is based on graph technology, it is specified using PROGRES and the UPGRADE framework. The tools for the architect are integrated to the in-dustrial CAD tool ArchiCAD. Consistency between knowledge and conceptual design is en-sured by the constraint checker, another extension to ArchiCAD.}, subject = {CAD}, language = {en} }