Using a Workflow Management Platform in Textual Data Management
(Triet Ho Anh Doan, Sven Bingert, Ramin Yahyapour),
2022-01-01
DOI
2020
OCR-D kompakt: Ergebnisse und Stand der Forschung in der Förderinitiative
(Konstantin Baierer, Matthias Boenig, Elisabeth Engl, Clemens Neudecker, Reinhard Altenhöner, Alexander Geyken, Johannes Mangei, Rainer Stotzka, Andreas Dengel, Martin Jenckel, Alexander Gehrke, Frank Puppe, Stefan Weil, Robert Sachunsky, Lena K. Schiffer, Maciej Janicki, Gerhard Heyer, Florian Fink, Klaus U. Schulz, Nikolaus Weichselbaumer, Saskia Limbach, Mathias Seuret, Rui Dong, Manuel Burghardt, Vincent Christlein, Triet Ho Anh Doan, Zeki Mustafa Dogan, Jörg-Holger Panzer, Kristine Schima-Voigt, Philipp Wieder),
2020-01-01
URL
OLA-HD – Ein OCR-D-Langzeitarchiv für historische Drucke
(Triet Ho Anh Doan, Zeki Mustafa Doğan, Jörg-Holger Panzer, Kristine Schima-Voigt, Philipp Wieder),
2020-01-01
BibTeX: Using a Workflow Management Platform in Textual Data Management
@article{2_136421,
abstract = {"Abstract The paper gives a brief introduction about the workflow management platform, Flowable, and how it is used for textual-data management. It is relatively new with its first release on 13 October, 2016. Despite the short time on the market, it seems to be quickly well-noticed with 4.6 thousand stars on GitHub at the moment. The focus of our project is to build a platform for text analysis on a large scale by including many different text resources. Currently, we have successfully connected to four different text resources and obtained more than one million works. Some resources are dynamic, which means that they might add more data or modify their current data. Therefore, it is necessary to keep data, both the metadata and the raw data, from our side up to date with the resources. In addition, to comply with FAIR principles, each work is assigned a persistent identifier (PID) and indexed for searching purposes. In the last step, we perform some standard analyses on the data to enhance our search engine and to generate a knowledge graph. End-users can utilize our platform to search on our data or get access to the knowledge graph. Furthermore, they can submit their code for their analyses to the system. The code will be executed on a High-Performance Cluster (HPC) and users can receive the results later on. In this case, Flowable can take advantage of PIDs for digital objects identification and management to facilitate the communication with the HPC system. As one may already notice, the whole process can be expressed as a workflow. A workflow, including error handling and notification, has been created and deployed. Workflow execution can be triggered manually or after predefined time intervals. According to our evaluation, the Flowable platform proves to be powerful and flexible. Further usage of the platform is already planned or implemented for many of our projects."},
author = {Triet Ho Anh Doan and Sven Bingert and Ramin Yahyapour},
doi = {10.1162/dint_a_00139},
grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/136421},
month = {01},
title = {Using a Workflow Management Platform in Textual Data Management},
type = {article},
year = {2022},
}
BibTeX: OLA-HD – Ein OCR-D-Langzeitarchiv für historische Drucke
@article{2_116509,
author = {Triet Ho Anh Doan and Zeki Mustafa Doğan and Jörg-Holger Panzer and Kristine Schima-Voigt and Philipp Wieder},
grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/116509},
month = {01},
title = {OLA-HD – Ein OCR-D-Langzeitarchiv für historische Drucke},
type = {article},
year = {2020},
}
BibTeX: OCR-D kompakt: Ergebnisse und Stand der Forschung in der Förderinitiative
@misc{2_121682,
abstract = {"Bereits seit einigen Jahren werden große Anstrengungen unternommen, um die im deutschen Sprachraum erschienenen Drucke des 16.-18. Jahrhunderts zu erfassen und zu digitalisieren. Deren Volltexttransformation konzeptionell und technisch vorzubereiten, ist das übergeordnete Ziel des DFG-Projekts OCR-D, das sich mit der Weiterentwicklung von Verfahren der Optical Character Recognition befasst. Der Beitrag beschreibt den aktuellen Entwicklungsstand der OCR-D-Software und analysiert deren erste Teststellung in ausgewählten Bibliotheken."},
author = {Konstantin Baierer and Matthias Boenig and Elisabeth Engl and Clemens Neudecker and Reinhard Altenhöner and Alexander Geyken and Johannes Mangei and Rainer Stotzka and Andreas Dengel and Martin Jenckel and Alexander Gehrke and Frank Puppe and Stefan Weil and Robert Sachunsky and Lena K. Schiffer and Maciej Janicki and Gerhard Heyer and Florian Fink and Klaus U. Schulz and Nikolaus Weichselbaumer and Saskia Limbach and Mathias Seuret and Rui Dong and Manuel Burghardt and Vincent Christlein and Triet Ho Anh Doan and Zeki Mustafa Dogan and Jörg-Holger Panzer and Kristine Schima-Voigt and Philipp Wieder},
grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121682},
month = {01},
title = {OCR-D kompakt: Ergebnisse und Stand der Forschung in der Förderinitiative},
type = {misc},
url = {https://publications.goettingen-research-online.de/handle/2/116509},
year = {2020},
}
menoci: Lightweight Extensible Web Portal enabling FAIR Data Management for Biomedical Research Projects
(Markus Suhr, Christoph Lehmann, Christian R. K. D. Bauer, Theresa Bender, Cornelius Knopp, Luca Freckmann, Björn Öst Hansen, Christian Henke, Georg Aschenbrandt, Lea Katharina Kühlborn, Sophia Rheinländer, Linus Weber, Bartlomiej Marzec, Marcel Hellkamp, Philipp Wieder, Harald Kusch, Ulrich Sax, Sara Yasemin Nussbeck),
2020-01-01
DOI
BibTeX: menoci: Lightweight Extensible Web Portal enabling FAIR Data Management for Biomedical Research Projects
@misc{2_63412,
abstract = {"Background: Biomedical research projects deal with data management requirements from multiple sources like funding agencies' guidelines, publisher policies, discipline best practices, and their own users' needs. We describe functional and quality requirements based on many years of experience implementing data management for the CRC 1002 and CRC 1190. A fully equipped data management software should improve documentation of experiments and materials, enable data storage and sharing according to the FAIR Guiding Principles while maximizing usability, information security, as well as software sustainability and reusability. Results: We introduce the modular web portal software menoci for data collection, experiment documentation, data publication, sharing, and preservation in biomedical research projects. Menoci modules are based on the Drupal content management system which enables lightweight deployment and setup, and creates the possibility to combine research data management with a customisable project home page or collaboration platform. Conclusions: Management of research data and digital research artefacts is transforming from individual researcher or groups best practices towards project- or organisation-wide service infrastructures. To enable and support this structural transformation process, a vital ecosystem of open source software tools is needed. Menoci is a contribution to this ecosystem of research data management tools that is specifically designed to support biomedical research projects."},
author = {Markus Suhr and Christoph Lehmann and Christian R. K. D. Bauer and Theresa Bender and Cornelius Knopp and Luca Freckmann and Björn Öst Hansen and Christian Henke and Georg Aschenbrandt and Lea Katharina Kühlborn and Sophia Rheinländer and Linus Weber and Bartlomiej Marzec and Marcel Hellkamp and Philipp Wieder and Harald Kusch and Ulrich Sax and Sara Yasemin Nussbeck},
doi = {10.48550/arXiv.2002.06161},
grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/63412},
month = {01},
title = {menoci: Lightweight Extensible Web Portal enabling FAIR Data Management for Biomedical Research Projects},
type = {misc},
year = {2020},
}
Enhanced Research for the Göttingen Campus
(Jens Dierkes, Timo Gnadt, Fabian Cremer, Péter Király, Christopher Menke, Oliver Wannenwetsch, Lena Steilen, Ulrike Wuttke, Wolfram Horstmann, Ramin Yahyapour),
2015-01-01
BibTeX: Enhanced Research for the Göttingen Campus
@inproceedings{2_57543,
author = {Jens Dierkes and Timo Gnadt and Fabian Cremer and Péter Király and Christopher Menke and Oliver Wannenwetsch and Lena Steilen and Ulrike Wuttke and Wolfram Horstmann and Ramin Yahyapour},
grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/57543},
month = {01},
title = {Enhanced Research for the Göttingen Campus},
type = {inproceedings},
year = {2015},
}
