@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} }