@inproceedings{gradl2026_117723,
  title = {Future Applications : The Text+Registry as Reusable Technical Component Beyond Resource Cataloguing},
  author = {Gradl, Tobias and Fruth, Leon and Geißler, Nils and Hensen, Kilian Erasmus and Schulz, Daniela},
  year = {2026},
  pages = {166-174},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-117723x},
  url = {https://fis.uni-bamberg.de/handle/uniba/117723},
  language = {eng},
  abstract = {Digital humanities research software and infrastructures are typically designed around highly specific scholarly requirements. While effective for particular research practices, they often lack transferability across domains. The Text+ Registry, developed within the Text+ consortium of the German National Research Data Infrastructure (NFDI), proposes an alternative approach. Rather than serving solely as a catalogue for editions, lexical resources, and collections, it is conceived as a reusable infrastructural component adaptable to diverse scholarly and institutional contexts.
This paper examines three architectural principles underlying the Registry: metamodelling, model-driven design, and information layering.
Furthermore, two application scenarios demonstrate broader reuse: a transnational meta-archive of German archival materials on modern India (MIDA) and a planned NFDI-wide helpdesk catalogue for research data management services.
Technically, the Registry harvests distributed data via standard protocols while aligning heterogeneous schemas through configurable mappings.
The Text+ Registry thus models an infrastructural philosophy that supports pluralism: different conceptual frameworks can coexist and interoperate without enforced standardization. This approach reconciles disciplinary specificity, interoperability, automation, and curation, offering a sustainable model for digital humanities infrastructures and potentially for research infrastructures beyond the humanities.},
  keywords = {Text+, Text+ Registry, Resource Catalog, Research Infrastructure, NFDI, MIDA}
}

@inproceedings{gradl2026_117769,
  title = {Future Applications : The Text+Registry as Reusable Technical Component Beyond Resource Cataloguing},
  author = {Gradl, Tobias and Fruth, Leon and Geißler, Nils and Hensen, Kilian Erasmus and Schulz, Daniela},
  year = {2026},
  booktitle = {European Association for Digital Humanities 2026 : "Linking Europe: Digital Humanities Without Borders"},
  pages = {166-174},
  publisher = {Zenodo},
  isbn = {978-83-977695-1-9},
  doi = {10.5281/zenodo.23363983},
  url = {https://fis.uni-bamberg.de/handle/uniba/117769},
  language = {eng},
  abstract = {Digital humanities research software and infrastructures are typically designed around highly specific scholarly requirements. While effective for particular research practices, they often lack transferability across domains. The Text+ Registry, developed within the Text+ consortium of the German National Research Data Infrastructure (NFDI), proposes an alternative approach. Rather than serving solely as a catalogue for editions, lexical resources, and collections, it is conceived as a reusable infrastructural component adaptable to diverse scholarly and institutional contexts.
This paper examines three architectural principles underlying the Registry: metamodelling, model-driven design, and information layering.
Furthermore, two application scenarios demonstrate broader reuse: a transnational meta-archive of German archival materials on modern India (MIDA) and a planned NFDI-wide helpdesk catalogue for research data management services.
Technically, the Registry harvests distributed data via standard protocols while aligning heterogeneous schemas through configurable mappings.
The Text+ Registry thus models an infrastructural philosophy that supports pluralism: different conceptual frameworks can coexist and interoperate without enforced standardization. This approach reconciles disciplinary specificity, interoperability, automation, and curation, offering a sustainable model for digital humanities infrastructures and potentially for research infrastructures beyond the humanities.},
  keywords = {Text+, Text+ Registry, Resource Catalog, Research Infrastructure, NFDI, MIDA}
}

@inproceedings{fruth2026_115320,
  title = {ADISS : Authority Data Integration Search System},
  author = {Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  year = {2026},
  pages = {189-200},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  url = {https://fis.uni-bamberg.de/handle/uniba/115320},
  language = {eng},
  abstract = {This paper introduces ADISS, a generic search system designed to integrate heterogeneous authority file providers. Authority data is used to unambiguously identify entities such as persons, places, and organizations. As single data providers do not offer both quantity and quality of data, a combined access to multiple datasets is often required to support real-world use cases. In the context of Digital Humanities this combination improves the resolution of ambiguities in data curation processes. Our work is mainly motivated by two projects that require semi-automatic retrieval, as well as user-centered search scenarios for different authority file providers. Instead of using multiple existing endpoints to access the various datasets, we gather the heterogeneous data and make it accessible via integrated query and result models. In this paper, we present our highly configurable search API, which offers a diverse range of search and filtering options. We show that by its generic and highly configurable nature, our system is adaptable and reusable for a diverse set of use cases and conclude the paper with ideas for further steps and improvements.},
  keywords = {FAIR, Digital Humanities, Authority Data, Data Curation}
}

@inproceedings{hebeis2026_114779,
  title = {Automatisierte Typklassifikation von Normdaten mit BERT : Poster},
  author = {Hebeis, Maximilian and Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  year = {2026},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114779x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114779},
  language = {deu},
  abstract = {Normdaten sind zentral für die Interoperabilität geisteswissenschaftlicher Daten. Die an der Otto-Friedrich-Universität Bamberg entwickelte integrierte Suchplattform ADISS integriert verschiedene Normdatenquellen wie GND, Wikidata oder Geonames, jedoch bislang ohne einheitliche Typisierung. Dies erschwert eine gezielte Facettierung bei der Suche. Ziel des Projekts ist daher ein System zur automatisierten Typenzuordnung mittels maschinellen Lernens. Auf Basis von BERT soll ein Klassifikator trainiert werden, der Normdatensätze in ein reduziertes Zielschema überführt. Trainingsdaten entstehen durch Mapping zwischen GND- und Wikidata-Datensätzen. Neben Quelltypen werden Name und Beschreibung des jeweiligen Normdatensatzes als semantische Features genutzt. Erste Experimente mit einem auf einem multilingualen BERT-Modell als Encoder basierenden hierarchischen Klassifikator zeigen vielversprechende Ergebnisse. Künftig sollen die Datenbasis und Modellparameter optimiert werden, um eine robuste, domänenübergreifende Typisierung zur Verbesserung der Suchfunktionalität in ADISS zu ermöglichen.},
  keywords = {Normdaten, Textklassifikation, Maschinelles Lernen, Forschungsdateninfrastrukturen, Metadaten, Entity Typing, BERT, Datenintegration}
}

@inproceedings{hebeis2026_114771,
  title = {Automatisierte Typklassifikation von Normdaten mit BERT},
  author = {Hebeis, Maximilian and Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  year = {2026},
  pages = {447-450},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114771x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114771},
  language = {deu},
  abstract = {Normdaten sind zentral für die Interoperabilität geisteswissenschaftlicher Daten. Die an der Otto-Friedrich-Universität Bamberg entwickelte integrierte Suchplattform ADISS integriert verschiedene Normdatenquellen wie GND, Wikidata oder Geonames, jedoch bislang ohne einheitliche Typisierung. Dies erschwert eine gezielte Facettierung bei der Suche. Ziel des Projekts ist daher ein System zur automatisierten Typenzuordnung mittels maschinellen Lernens. Auf Basis von BERT soll ein Klassifikator trainiert werden, der Normdatensätze in ein reduziertes Zielschema überführt. Trainingsdaten entstehen durch Mapping zwischen GND- und Wikidata-Datensätzen. Neben Quelltypen werden Name und Beschreibung des jeweiligen Normdatensatzes als semantische Features genutzt. Erste Experimente mit einem auf einem multilingualen BERT-Modell als Encoder basierenden hierarchischen Klassifikator zeigen vielversprechende Ergebnisse. Künftig sollen die Datenbasis und Modellparameter optimiert werden, um eine robuste, domänenübergreifende Typisierung zur Verbesserung der Suchfunktionalität in ADISS zu ermöglichen.},
  keywords = {Normdaten, Textklassifikation, Maschinelles Lernen, Forschungsdateninfrastrukturen, Metadaten, Entity Typing, BERT, Datenintegration}
}

@inproceedings{hebeis2026_114773,
  title = {Automatisierte Typklassifikation von Normdaten mit BERT},
  author = {Hebeis, Maximilian and Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  year = {2026},
  booktitle = {Book of Abstracts : DHd 2026},
  pages = {447-450},
  publisher = {Zenodo},
  doi = {10.5281/zenodo.18703020},
  url = {https://fis.uni-bamberg.de/handle/uniba/114773},
  language = {deu},
  abstract = {Normdaten sind zentral für die Interoperabilität geisteswissenschaftlicher Daten. Die an der Otto-Friedrich-Universität Bamberg entwickelte integrierte Suchplattform ADISS integriert verschiedene Normdatenquellen wie GND, Wikidata oder Geonames, jedoch bislang ohne einheitliche Typisierung. Dies erschwert eine gezielte Facettierung bei der Suche. Ziel des Projekts ist daher ein System zur automatisierten Typenzuordnung mittels maschinellen Lernens. Auf Basis von BERT soll ein Klassifikator trainiert werden, der Normdatensätze in ein reduziertes Zielschema überführt. Trainingsdaten entstehen durch Mapping zwischen GND- und Wikidata-Datensätzen. Neben Quelltypen werden Name und Beschreibung des jeweiligen Normdatensatzes als semantische Features genutzt. Erste Experimente mit einem auf einem multilingualen BERT-Modell als Encoder basierenden hierarchischen Klassifikator zeigen vielversprechende Ergebnisse. Künftig sollen die Datenbasis und Modellparameter optimiert werden, um eine robuste, domänenübergreifende Typisierung zur Verbesserung der Suchfunktionalität in ADISS zu ermöglichen.},
  keywords = {Normdaten, Textklassifikation, Maschinelles Lernen, Forschungsdateninfrastrukturen, Metadaten, Entity Typing, BERT, Datenintegration}
}

@inproceedings{hebeis2026_114772,
  title = {Automatisierte Typklassifikation von Normdaten mit BERT : Poster},
  author = {Hebeis, Maximilian and Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  year = {2026},
  publisher = {Zenodo},
  doi = {10.5281/zenodo.18999712},
  url = {https://fis.uni-bamberg.de/handle/uniba/114772},
  language = {deu},
  abstract = {Normdaten sind zentral für die Interoperabilität geisteswissenschaftlicher Daten. Die an der Otto-Friedrich-Universität Bamberg entwickelte integrierte Suchplattform ADISS integriert verschiedene Normdatenquellen wie GND, Wikidata oder Geonames, jedoch bislang ohne einheitliche Typisierung. Dies erschwert eine gezielte Facettierung bei der Suche. Ziel des Projekts ist daher ein System zur automatisierten Typenzuordnung mittels maschinellen Lernens. Auf Basis von BERT soll ein Klassifikator trainiert werden, der Normdatensätze in ein reduziertes Zielschema überführt. Trainingsdaten entstehen durch Mapping zwischen GND- und Wikidata-Datensätzen. Neben Quelltypen werden Name und Beschreibung des jeweiligen Normdatensatzes als semantische Features genutzt. Erste Experimente mit einem auf einem multilingualen BERT-Modell als Encoder basierenden hierarchischen Klassifikator zeigen vielversprechende Ergebnisse. Künftig sollen die Datenbasis und Modellparameter optimiert werden, um eine robuste, domänenübergreifende Typisierung zur Verbesserung der Suchfunktionalität in ADISS zu ermöglichen.},
  keywords = {Normdaten, Textklassifikation, Maschinelles Lernen, Forschungsdateninfrastrukturen, Metadaten, Entity Typing, BERT, Datenintegration}
}

@inproceedings{fruth2026_114695,
  title = {Cataloguing Editions and Other Resources in One Unified System : The Case of the Text+ Registry},
  author = {Fruth, Leon and Geißler, Nils and Gradl, Tobias and Schulz, Daniela},
  year = {2026},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114695x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114695},
  language = {eng},
  abstract = {Text+ is a consortium of the German National Research Data Infrastructure (Nationale Forschungsdateninfrastruktur, NFDI). With an initial focus on the three data domains collections, lexical resources, and editions, Text+ aims at constructing a research data infrastructure that is both flexible and scalable, catering to the unique requirements of academic disciplines that work with textual and linguistic data, but also beyond. Its goal is to further develop standards and best practices to make data available according to the FAIR principles (Findable, Accessible, Interoperable, Reusable). As an initiative of the community for the community, the consortium provides a whole range of services, data and consulting for institutions, projects and individual researchers. 

One pivotal component within the Text+ infrastructure is the Text+ Registry, which is designed as a unified cataloguing system for the diverse set of resources from the data domains. The Registry builds on data that has been gathered and made accessible by existing databases and catalogues (like Greta Franzini’s Dig-Ed-Cat and Patrick Sahle’s Catalog of Digital Scholarly Editions, library or union catalogues, research information systems of funding bodies such as AGATE). An often lacking integration with external knowledge bases and contextual biases (discipline, type of resource) in external sources are resolved by compiling descriptions from multiple sources wherever available and possible. Remaining gaps are filled in a manual curation layer by respective domain experts. In order to be able to accommodate the diverse resource landscape, the Registry is technologically based on a sophisticated metamodelling concept that allows the definition and evolution of dedicated data models for different types of resources, and enables the import, curation and provision of resource descriptions. APIs for data ingest from existing catalogues and data provision are provided, and search and retrieval tools such as the CLARIN Federated Content Search (FCS) and the DARIAH-DE Generic Search (GS) build on these interfaces. The Text+ Registry should not only increase the visibility of scientific resources, but also overcome the traditional barriers that hinder their discoverability and accessibility.

The data models in the Text+ Registry are tailored to different requirements for each data domain and were developed based on relevant subject-specific standards and best practices, as well as in direct collaboration with the communities (e.g. Specialised Information Services, SIS). The formalisation of relationships between collections, editions and lexical resources, as well as tools, actors and other entity types, creates a resource network that can also be expanded over and above Text+ to prepare for integration into further developments within the NFDI context such as knowledge graphs.

The paper presents the technologies and methodologies behind the Text+ Registry and reflects on challenges, opportunities but also limitations. Taking the data model for cataloguing editions as an example, the metamodelling approach as well as the architectural blueprint of the Text+ Registry are presented.},
  keywords = {Text+, Data Integration, Metadata Catalogues, Digital Humanities}
}

@article{fruth2026_112845,
  title = {A Flexible Search System for Integrated Authority Data : ADISS},
  author = {Fruth, Leon and Gradl, Tobias and Hebeis, Maximilian and Henrich, Andreas},
  year = {2026},
  pages = {167-178},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-112845x},
  url = {https://fis.uni-bamberg.de/handle/uniba/112845},
  language = {eng},
  abstract = {This paper presents ADISS, a generic and flexible search system designed to integrate heterogeneous authority file providers. Authority data is used to unambiguously identify entities such as persons, places, and institutions. As individual data providers typically do not offer both broad, universal coverage and domain-specific, in-depth data, many real-world application scenarios require combined access to multiple datasets. In the context of Digital Humanities, combining multiple authority data providers helps to improve the coverage and to resolve ambiguities more effectively during data curation. Instead of relying on separate endpoints to access multiple data sources, we address this need by aggregating the datasets and exposing them through integrated query and result models, thus simplifying access at the level of technical interfaces and schema integration. We present a highly configurable search API, which offers a diverse range of search and filtering options, to leverage the integrated data sources. We demonstrate its practical value through two active projects, that require semi-automatic retrieval, as well as user-centered search scenarios for different authority file providers. An evaluation based on manually curated data shows high retrieval accuracy, highlighting the system’s effectiveness. We further illustrate how ADISS’s generic and highly configurable design makes it adaptable and reusable for a wide range of use cases, and we outline directions for future improvements.},
  keywords = {FAIR, Digital Humanities, Authority Data, Data Curation}
}

@inproceedings{fruth2025_114701,
  title = {Cataloguing Editions and Other Resources in One Unified System : The Case of the Text+ Registry},
  author = {Fruth, Leon and Geißler, Nils and Gradl, Tobias and Schulz, Daniela},
  year = {2025},
  booktitle = {Proceedings of the Digital Humanities Congress 2024},
  publisher = {The Digital Humanities Institute (DHI)},
  address = {Sheffield},
  url = {https://fis.uni-bamberg.de/handle/uniba/114701},
  language = {eng},
  abstract = {Text+ is a consortium of the German National Research Data Infrastructure (Nationale Forschungsdateninfrastruktur, NFDI). With an initial focus on the three data domains collections, lexical resources, and editions, Text+ aims at constructing a research data infrastructure that is both flexible and scalable, catering to the unique requirements of academic disciplines that work with textual and linguistic data, but also beyond. Its goal is to further develop standards and best practices to make data available according to the FAIR principles (Findable, Accessible, Interoperable, Reusable). As an initiative of the community for the community, the consortium provides a whole range of services, data and consulting for institutions, projects and individual researchers. 

One pivotal component within the Text+ infrastructure is the Text+ Registry, which is designed as a unified cataloguing system for the diverse set of resources from the data domains. The Registry builds on data that has been gathered and made accessible by existing databases and catalogues (like Greta Franzini’s Dig-Ed-Cat and Patrick Sahle’s Catalog of Digital Scholarly Editions, library or union catalogues, research information systems of funding bodies such as AGATE). An often lacking integration with external knowledge bases and contextual biases (discipline, type of resource) in external sources are resolved by compiling descriptions from multiple sources wherever available and possible. Remaining gaps are filled in a manual curation layer by respective domain experts. In order to be able to accommodate the diverse resource landscape, the Registry is technologically based on a sophisticated metamodelling concept that allows the definition and evolution of dedicated data models for different types of resources, and enables the import, curation and provision of resource descriptions. APIs for data ingest from existing catalogues and data provision are provided, and search and retrieval tools such as the CLARIN Federated Content Search (FCS) and the DARIAH-DE Generic Search (GS) build on these interfaces. The Text+ Registry should not only increase the visibility of scientific resources, but also overcome the traditional barriers that hinder their discoverability and accessibility.

The data models in the Text+ Registry are tailored to different requirements for each data domain and were developed based on relevant subject-specific standards and best practices, as well as in direct collaboration with the communities (e.g. Specialised Information Services, SIS). The formalisation of relationships between collections, editions and lexical resources, as well as tools, actors and other entity types, creates a resource network that can also be expanded over and above Text+ to prepare for integration into further developments within the NFDI context such as knowledge graphs.

The paper presents the technologies and methodologies behind the Text+ Registry and reflects on challenges, opportunities but also limitations. Taking the data model for cataloguing editions as an example, the metamodelling approach as well as the architectural blueprint of the Text+ Registry are presented.},
  keywords = {Text+, Data Integration, Metadata Catalogues, Digital Humanities}
}

@inproceedings{gradl2025_112303,
  title = {Teilprojekt Text+ – Nutzbarmachung von Sammlungen, Editionen und Co},
  author = {Gradl, Tobias and Hirmer, Tobias and Fruth, Leon and Henrich, Andreas},
  year = {2025},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  doi = {10.20378/irb-112303},
  urn = {urn:nbn:de:bvb:473-irb-112303x},
  url = {https://fis.uni-bamberg.de/handle/uniba/112303},
  language = {deu},
  abstract = {Text+ ist ein Konsortium der Nationalen Forschungsdateninfrastruktur (NFDI) und bietet Zugang zu Knowhow, Standards und Services im Bereich der text- und sprachbasierten Wissenschaften. In Text+ ist das Team des Lehrstuhls Medieninformatik insbesondere mit Themen rund um die Erschließung und Nutzbarmachung von Datenbeständen befasst. Dabei werden die Anbieter von Forschungsdaten, die sogenannten Datenzentren, bei der Umsetzung der FAIR Prinzipien unterstützt. Über die anbieterorientierte Perspektive hinaus stehen Anforderungen durch die Fachwissenschaften in der Forschung im Vordergrund. Anforderungen aus DiSo an die über Text+ zugänglichen Ressourcen können für die Gestaltung von Diensten und Standards mit Blick auf die Nachnutzbarkeit in Unterricht und Lehrkräftebildung eingebracht und berücksichtigt werden.},
  keywords = {DiSo, lernen:digital}
}

@article{fruth2025_111276,
  title = {A Flexible Search System for Integrated Authority Data : ADISS},
  author = {Fruth, Leon and Gradl, Tobias and Hebeis, Maximilian and Henrich, Andreas},
  year = {2025},
  journal = {Datenbank-Spektrum : Zeitschrift für Datenbanktechnologie ; Organ der Fachgruppe Datenbanken der Gesellschaft für Informatik e.V.},
  volume = {25},
  number = {3},
  pages = {167-178},
  publisher = {Springer},
  address = {Berlin ; Heidelberg},
  issn = {1618-2162},
  doi = {10.1007/s13222-025-00515-7},
  url = {https://fis.uni-bamberg.de/handle/uniba/111276},
  language = {eng},
  abstract = {This paper presents ADISS, a generic and flexible search system designed to integrate heterogeneous authority file providers. Authority data is used to unambiguously identify entities such as persons, places, and institutions. As individual data providers typically do not offer both broad, universal coverage and domain-specific, in-depth data, many real-world application scenarios require combined access to multiple datasets. In the context of Digital Humanities, combining multiple authority data providers helps to improve the coverage and to resolve ambiguities more effectively during data curation. Instead of relying on separate endpoints to access multiple data sources, we address this need by aggregating the datasets and exposing them through integrated query and result models, thus simplifying access at the level of technical interfaces and schema integration. We present a highly configurable search API, which offers a diverse range of search and filtering options, to leverage the integrated data sources. We demonstrate its practical value through two active projects, that require semi-automatic retrieval, as well as user-centered search scenarios for different authority file providers. An evaluation based on manually curated data shows high retrieval accuracy, highlighting the system’s effectiveness. We further illustrate how ADISS’s generic and highly configurable design makes it adaptable and reusable for a wide range of use cases, and we outline directions for future improvements.},
  keywords = {FAIR, Digital Humanities, Authority Data, Data Curation}
}

@inproceedings{gradl2025_106485,
  title = {Extending Data Models by Declaratively Specifying Contextual Knowledge},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2025},
  pages = {123-126},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1064857},
  url = {https://fis.uni-bamberg.de/handle/uniba/106485},
  language = {eng},
  abstract = {The research data landscape of the arts and humanities is characterized by a high degree of heterogeneity. To improve interoperability, recent initiatives and research infrastructures are encouraging the use of standards and best practices. However, custom data models are often considered necessary to exactly reflect the requirements of a particular collection or research project. To address the needs of scholars in the arts and humanities for a composition of research data irrespective of the degree of structuredness and standardization, we propose a concept on the basis of formal languages, which facilitates declarative data modeling by respective domain experts. By identifying and defining grammatical patterns and deriving transformation functions, the structure of data is generated or extended in accordance with the particular context and needs of the domain.},
  keywords = {digital humanities, descriptive data modeling, language applications, DARIAH}
}

@inproceedings{gradl2025_106381,
  title = {Data Integration for the Arts and Humanities : A Language Theoretical Concept},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2025},
  pages = {281-293},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  series = {Lecture Notes in Computer Science},
  urn = {urn:nbn:de:bvb:473-irb-1063811},
  url = {https://fis.uni-bamberg.de/handle/uniba/106381},
  language = {eng},
  abstract = {In the context of the arts and humanities, heterogeneity largely corresponds to the variety of disciplines, their research questions and communities. Resulting from the diversity of the application domain, the analysis of overall requirements and the subsequent derivation of appropriate unifying schemata is prevented by the complexity and size of the domain. The approach presented in this paper is based on the hypothesis that data integration problems in the arts and humanities can be solved on the theoretical foundation of formal languages. In applying a theoretically substantiated framework, integrative solutions on the formal basis of language specifications can be tailored to specific and individual research needs—abstracting from reoccurring technical difficulties and leading the focus of domain experts on semantic aspects.},
  keywords = {Data Integration}
}

@article{henrich2025_106705,
  title = {DARIAH(-DE): Digital Research Infrastructure for the Arts and Humanities : Concepts and Perspectives},
  author = {Henrich, Andreas and Gradl, Tobias},
  year = {2025},
  pages = {47-58},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1067057},
  url = {https://fis.uni-bamberg.de/handle/uniba/106705},
  language = {eng},
  abstract = {DARIAH (Digital Research Infrastructure for the Arts and Humanities) is part of the European Strategy on Research Infrastructures. Among 38 projects originally on this roadmap, DARIAH is one of two projects addressing social sciences and humanities. According to its self-conception and its political mandate DARIAH has the mission to enhance and support digitally-enabled research across the humanities and arts. DARIAH aims to develop and maintain an infrastructure in support of ICT-based research practices. One main distinguishing aspect of DARIAH is that it is not focusing on one application domain but especially addresses the support of interdisciplinary research in the humanities and arts. The present paper first gives an overview on DARIAH as a whole and then focuses on the important aspect of technical, syntactic and semantic interoperability. Important aspects in this respect are metadata registries and crosswalk definitions allowing for meaningful cross-collection and inter-collection services and analysis.},
  keywords = {research infrastructure, digital humanities, DARIAH, DARIAH-DE}
}

@inproceedings{gradl2025_111016,
  title = {Filling the gaps : Facilitating access to enriched research data},
  author = {Gradl, Tobias},
  year = {2025},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-111016x},
  url = {https://fis.uni-bamberg.de/handle/uniba/111016},
  language = {eng},
  abstract = {The document discusses the challenges faced in managing and enriching research data in the Digital Humanities (DH). It highlights the role of research data repositories and platforms such as Gams, Zenodo, and Europeana in improving data visibility and accessibility. However, many data producers struggle with transforming their data into formats compatible with these infrastructures due to limited resources.

The document proposes a transformation service designed to assist data producers by describing data models, executing transformations, separating technological and domain aspects of data modeling. This service helps users enrich, cleanse, and process fragmented datasets into unified virtual datasets. It also supports the creation of virtual APIs to standardize and harmonize data access across various platforms.

Examples of successful implementations are provided, including a CLARIAH-DE project that made teaching materials accessible and the development of virtual datasets for research publications and geographical authority data. The service is undergoing further testing within the NFDI Text+ infrastructure and has received positive feedback from the academic community.},
  keywords = {research data}
}

@inproceedings{gradl2025_111116,
  title = {The Text+ Registry : Federating Research Data Catalogues for the Digital Humanities},
  author = {Gradl, Tobias and Fruth, Leon and Henrich, Andreas},
  year = {2025},
  booktitle = {Linking Theory and Practice of Digital Libraries : 29th International Conference on Theory and Practice of Digital Libraries, TPDL 2025, Tampere, Finland, September 23–26, 2025, Proceedings},
  pages = {378-394},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  isbn = {978-3-032-05409-8},
  doi = {10.1007/978-3-032-05409-8\_22},
  url = {https://fis.uni-bamberg.de/handle/uniba/111116},
  language = {eng}
}

@inproceedings{gradl2025_107009,
  title = {Judaica recherchieren : Unterstützung bei der Realisierung forschungsspezifischer Suchlösungen durch die generische Suche von DARIAH-DE},
  author = {Gradl, Tobias and Lordick, Harald and Henrich, Andreas},
  year = {2025},
  pages = {230-235},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1070092},
  url = {https://fis.uni-bamberg.de/handle/uniba/107009},
  language = {deu},
  abstract = {-},
  keywords = {Judaica}
}

@inproceedings{gradl2025_107010,
  title = {Nutzung und Kombination von Daten aus strukturierten und unstrukturierten Quellen zur Identifikation transnationaler Lebensläufe},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2025},
  pages = {261-265},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1070103},
  url = {https://fis.uni-bamberg.de/handle/uniba/107010},
  language = {deu},
  abstract = {-},
  keywords = {transnationale Lebensläufe}
}

@inproceedings{fruth2025_108435,
  title = {ADISS : Authority Data Integration Search System},
  author = {Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  editor = {Gesellschaft für Informatik, Bonn},
  year = {2025},
  booktitle = {Datenbanksysteme für Business, Technologie und Web : Workshopband (BTW 2025)},
  pages = {189-200},
  publisher = {Gesellschaft für Informatik},
  address = {Bonn},
  doi = {10.18420/btw2025-123},
  url = {https://fis.uni-bamberg.de/handle/uniba/108435},
  language = {eng},
  abstract = {This paper introduces ADISS, a generic search system designed to integrate heterogeneous authority file providers. Authority data is used to unambiguously identify entities such as persons, places, and organizations. As single data providers do not offer both quantity and quality of data, a combined access to multiple datasets is often required to support real-world use cases. In the context of Digital Humanities this combination improves the resolution of ambiguities in data curation processes. Our work is mainly motivated by two projects that require semi-automatic retrieval, as well as user-centered search scenarios for different authority file providers. Instead of using multiple existing endpoints to access the various datasets, we gather the heterogeneous data and make it accessible via integrated query and result models. In this paper, we present our highly configurable search API, which offers a diverse range of search and filtering options. We show that by its generic and highly configurable nature, our system is adaptable and reusable for a diverse set of use cases and conclude the paper with ideas for further steps and improvements.},
  keywords = {FAIR, Digital Humanities, Authority Data, Data Curation}
}

@article{gradl2024_105422,
  title = {Towards a Registry for Digital Resources : The Text+ Registry for Editions},
  author = {Gradl, Tobias and Kudella, Christoph and Lordick, Harald and Schulz, Daniela},
  year = {2024},
  pages = {151-160},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1054225},
  url = {https://fis.uni-bamberg.de/handle/uniba/105422},
  language = {eng},
  abstract = {The paper presents the Text+ Registry as a central system to describe and catalogue different kinds of resources. Using the example of editions and edition projects, desiderata and challenges regarding their discoverability are outlined, and the data model to cater for the wide range of different types of editions is described. With its overarching and flexible approach, the Text+ Registry is a versatile and flexible technical component, designed for future expansion and broad connectivity.},
  keywords = {Metamodelling, Discoverability, Editions, Research Infrastructure, FAIR}
}

@inproceedings{gradl2024_98105,
  title = {Filling the gaps : Facilitating access to enriched research data},
  author = {Gradl, Tobias},
  year = {2024},
  booktitle = {DH2024 Book of Abstracts},
  pages = {227-232},
  doi = {10.5281/zenodo.13752750},
  url = {https://fis.uni-bamberg.de/handle/uniba/98105},
  language = {eng},
  abstract = {The document discusses the challenges faced in managing and enriching research data in the Digital Humanities (DH). It highlights the role of research data repositories and platforms such as Gams, Zenodo, and Europeana in improving data visibility and accessibility. However, many data producers struggle with transforming their data into formats compatible with these infrastructures due to limited resources.

The document proposes a transformation service designed to assist data producers by describing data models, executing transformations, separating technological and domain aspects of data modeling. This service helps users enrich, cleanse, and process fragmented datasets into unified virtual datasets. It also supports the creation of virtual APIs to standardize and harmonize data access across various platforms.

Examples of successful implementations are provided, including a CLARIAH-DE project that made teaching materials accessible and the development of virtual datasets for research publications and geographical authority data. The service is undergoing further testing within the NFDI Text+ infrastructure and has received positive feedback from the academic community.},
  keywords = {research data}
}

@article{gradl2024_98005,
  title = {Towards a Registry for Digital Resources : The Text+ Registry for Editions},
  author = {Gradl, Tobias and Kudella, Christoph and Lordick, Harald and Schulz, Daniela},
  year = {2024},
  journal = {Datenbank-Spektrum : Zeitschrift für Datenbanktechnologie},
  volume = {24},
  number = {2},
  pages = {151-160},
  publisher = {Springer},
  address = {Berlin ; Heidelberg},
  issn = {1610-1995},
  doi = {10.1007/s13222-024-00479-0},
  url = {https://fis.uni-bamberg.de/handle/uniba/98005},
  language = {eng},
  abstract = {The paper presents the Text+ Registry as a central system to describe and catalogue different kinds of resources. Using the example of editions and edition projects, desiderata and challenges regarding their discoverability are outlined, and the data model to cater for the wide range of different types of editions is described. With its overarching and flexible approach, the Text+ Registry is a versatile and flexible technical component, designed for future expansion and broad connectivity.},
  keywords = {Metamodelling, Discoverability, Editions, Research Infrastructure, FAIR}
}

@incollection{henrich2024_95306,
  title = {Suchwerkzeuge für Sammlungen : Herausforderungen, Trends und Strategien},
  author = {Henrich, Andreas and Gradl, Tobias and Jegan, Robin},
  year = {2024},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-953062},
  url = {https://fis.uni-bamberg.de/handle/uniba/95306},
  language = {deu},
  abstract = {-},
  keywords = {Suchwerkzeuge}
}

@incollection{henrich2024_93235,
  title = {Suchwerkzeuge für Sammlungen : Herausforderungen, Trends und Strategien},
  author = {Henrich, Andreas and Gradl, Tobias and Jegan, Robin},
  year = {2024},
  booktitle = {Forschen in Sammlungen : Dynamiken, Transformationen, Perspektiven},
  pages = {57-77},
  publisher = {Wallstein},
  address = {Göttingen},
  isbn = {978-3-8353-3573-8},
  doi = {10.15499/kds-003-004},
  url = {https://fis.uni-bamberg.de/handle/uniba/93235},
  language = {deu},
  abstract = {-},
  keywords = {Suchwerkzeuge}
}

@inproceedings{jegan2024_93093,
  title = {Anforderungen an das Forschungsdatenmanagement an einer mittelgroßen Universität und Konzeption einer prototypischen Lösung},
  author = {Jegan, Robin and Gradl, Tobias and Henrich, Andreas},
  year = {2024},
  pages = {274-275},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-930935},
  url = {https://fis.uni-bamberg.de/handle/uniba/93093},
  language = {deu},
  abstract = {-},
  keywords = {Forschungsdatenmanagement}
}

@inproceedings{gradl2024_93096,
  title = {Die DARIAH-DE Architektur zur forschungsorientierten Föderation von Kollektionen in den Digital Humanities},
  author = {Gradl, Tobias and Plutte, Christoph and Henrich, Andreas},
  year = {2024},
  pages = {1-8},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-930967},
  url = {https://fis.uni-bamberg.de/handle/uniba/93096},
  language = {deu},
  abstract = {In diesem Beitrag stellen wir eine neuartige Föderationsarchitektur vor, die auf eine Erfassung und Fall-basierte Zusammenführung von Forschungsdaten nach den individuellen Bedürfnissen von Forschungsprojekten abzielt. Digitale Sammlungen werden zentral verzeichnet, zur Vermeidung von Informationsverlusten jedoch nicht harmonisiert, sondern in Form von Beziehungen auf Schemaebene assoziiert, wodurch die Verwendung einer dynamisch föderierten Datenbasis in breiten und interdisziplinären, wie auch in fachspezifischen Anwendungskontexten ermöglicht werden kann},
  keywords = {DARIAH-DE Architektur, Digital Humanities}
}

@misc{albrecht2023_96243,
  title = {uni.vers Forschung : das Magazin der Otto-Friedrich-Universität Bamberg},
  author = {Albrecht, Stephan and Holl, Kristina and Bellendorf, Paul and Diederich, Viviane and Schreg, Rainer and Wittmann, Barbara and Redepenning, Marc and Scheunpflug, Annette and Franz, Julia and Kühn, Claudia and Keldenich, Georg-Vincent and Alzheimer, Heidrun and Vinken, Gerhard and Brassat, Wolfgang and Wagner, Bettina and Henrich, Andreas and Gradl, Tobias and Wings, Oliver},
  editor = {Fischbach, Kai},
  year = {2023},
  number = {Mai 23, Historisches und kulturelles Erbe – zwischen Bedrohung und Chance = Historical and Cultural Heritage - Between threat and opportunity},
  pages = {1-48},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  series = {uni.vers Forschung : das Magazin der Otto-Friedrich-Universität Bamberg},
  issn = {1618-9019},
  urn = {urn:nbn:de:bvb:473-irb-962432},
  url = {https://fis.uni-bamberg.de/handle/uniba/96243},
  language = {deu},
  abstract = {Vor 30 Jahren wurde die Stadt Bamberg in die UNESCO-Welterbeliste aufgenommen – das ist ein Grund zur Freude. Wir gratulieren herzlich mit dieser Ausgabe!

Die Bewahrung kulturellen Erbes stellt uns aber auch vor vielfältige Herausforderungen und gibt mitunter Grund zur Sorge. Lesen Sie, wie Bamberger Wissenschaftler*innen sich mit Fragestellungen zum historischen und kulturellen Erbe der Menschheit auseinandersetzen.},
  keywords = {Kulturerbe, Kulturgutsicherung, Kulturguterhaltung, Kunstgeschichte, Archäologie, Denkmalpflege}
}

@incollection{henrich2023_91864,
  title = {Integration von Forschungsdaten : Wie können Forschungsinfrastrukturen helfen?},
  author = {Henrich, Andreas and Gradl, Tobias},
  year = {2023},
  pages = {749-762},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-918641},
  url = {https://fis.uni-bamberg.de/handle/uniba/91864},
  language = {deu},
  abstract = {-},
  keywords = {Forschungsdaten}
}

@article{gradl2023_91872,
  title = {Die DARIAH-DE-Föderationsarchitektur : Datenintegration im Spannungsfeld forschungsspezifischer und domänenübergreifender Anforderungen},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2023},
  pages = {222-228},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-918725},
  url = {https://fis.uni-bamberg.de/handle/uniba/91872},
  language = {deu},
  abstract = {Dieser Beitrag gibt einen Überblick über die Konzepte und Komponenten der DARIAH-DE-Föderationsarchitektur. Nach einer Abgrenzung grundlegender Anforderungen forschungsspezifischer und domänenübergreifender Integration wird zwischen dem Erstellungs- und Verwendungskontext von Forschungsdaten unterschieden und verdeutlicht, wie die Föderationsarchitektur bei deren Modellierung unterstützt. Die Anwendung im Rahmen der generischen Suche zeigt abschließend, wie in dieser Umgebung generische und forschungsspezifische Anfragen unterstützt werden können.},
  keywords = {Forschungsdaten, Integration, Föderation, generische Suche, DARIAH-DE, research data, integration, federation, generic search, DARIAH-DE}
}

@article{henrich2023_92393,
  title = {Erforschung der Weltenwanderer : Über die Nutzung der Wikipedia zur Identifikation grenzüberschreitender Lebensläufe},
  author = {Henrich, Andreas and Gradl, Tobias},
  year = {2023},
  pages = {46-49},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-923939},
  url = {https://fis.uni-bamberg.de/handle/uniba/92393},
  language = {deu},
  abstract = {Für die Geschichtswissenschaften können die Datenbestände von Wikipedia und Wikidata wertvoll sein. Dies betrifft etwa die Erforschung von Biografien: War jemand im 19. Jahr-hundert bereits international vernetzt? Die Nationalbiografien geben hierüber mitunter nur unzureichend Auskunft, da die nationale Perspektive überwiegt. Wikipedia und Wikidata liefern wertvolle zusätzliche Informationen. Für die Auswertung der Daten entwickelt die Bamberger Medieninformatik derzeit einen Prototypen, Historiker und Informatiker arbeiten Hand in Hand.},
  keywords = {Wikipedia}
}

@article{gradl2023_90215,
  title = {Heterogene Daten in den Digital Humanities : Eine Architektur zur forschungsorientierten Föderation von Kollektionen},
  author = {Gradl, Tobias and Henrich, Andreas and Plutte, Christoph},
  year = {2023},
  pages = {1-10},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-902154},
  url = {https://fis.uni-bamberg.de/handle/uniba/90215},
  language = {deu},
  abstract = {Traditionelle Ansätze der Datenintegration basieren zumeist auf einer Harmonisierung heterogener Daten im Rahmen einer übergeordneten, integrativen Datenstruktur wie einem globalen Schema oder einer globalen Ontologie. Der vorliegende Beitrag verdeutlicht die Limitationen eines derartigen Harmonisierungsansatzes für den speziellen Kontext der Digital Humanities und zeigt, wie im Rahmen von DARIAH-DE eine forschungsorientierte und fallbasierte Föderation von Daten erreicht werden kann. Mit Hilfe von Collection, Schema und Crosswalk Registry können durch die Registrierung und Assoziation von Kollektionen und darin verwendeten Datenschemata sowohl übergreifende als auch disziplinspezifische Sichten auf Forschungsdaten geschaffen werden.},
  keywords = {Datenintegration, Digital Humanities, Softwaresystem}
}

@inproceedings{gradl2023_90490,
  title = {A novel approach for a reusable federation of research data within the arts and humanities},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2023},
  pages = {1-6},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-904903},
  url = {https://fis.uni-bamberg.de/handle/uniba/90490},
  language = {eng},
  abstract = {In distributed systems literature the orthogonal but interdependent characteristics of autonomy, distribution and heterogeneity are used to classify distributed systems. From a holistic perspective on the arts and humanities, collections have evolved over decades or centuries from highly autonomous disciplines and institutions and are widely spread, which resulted in heterogeneous perspectives and data models. Despite its negative notion as data integration problem, the term heterogeneity also symbolizes the diversity of research methodologies within the disciplines of the arts and humanities. Resolving heterogeneity hence implies an abstraction from the specifics that are valuable for focused disciplinary and interdisciplinary research projects.
Our approach presents a novel concept for data federation in the arts and humanities, which focuses the needs of research projects as well as interdisciplinary and broad use-cases. We especially address the reusability of explicated knowledge on correlations between schemata and digital collections and show where domain experts are required to bridge semantic gaps.},
  keywords = {data integration, data federation, digital humanities, research data, DARIAH-DE}
}

@inproceedings{gradl2023_90497,
  title = {Explicating knowledge on data models through domain specific languages},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2023},
  pages = {1125-1136},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  series = {Gesellschaft für Informatik: GI-Edition / Proceedings},
  urn = {urn:nbn:de:bvb:473-irb-904979},
  url = {https://fis.uni-bamberg.de/handle/uniba/90497},
  language = {eng},
  abstract = {Digital artifacts and metadata of the arts and humanities exhibit a wide spectrum of formats, structures and contexts, and hence a high level of heterogeneity. With particular respect of the characteristics of the application domain, we propose a concept on the basis of formal languages, which allows the separation of technical and contextual aspects of data modeling. Based on a developed framework, domain experts explicate knowledge about data in terms of domain specific languages and derived transformation functions. Independent of actual technical aspects of data transformation and integration (e.g. formats, access protocols, schema languages), experts of particular disciplines, collections or research questions can describe and define data models and relations in an extensive, declarative fashion—utilizing custom data models or standards as applicable. As implicit knowledge is continuously explicated within the data models, interpretations external to the generative context of data are facilitated—thereby promoting interoperability.},
  keywords = {digital humanities, descriptive data modeling, language applications, DARIAH}
}

@incollection{henrich2023_90099,
  title = {Data Retrieval},
  author = {Henrich, Andreas and Jegan, Robin and Gradl, Tobias},
  year = {2023},
  pages = {427-450},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-900996},
  url = {https://fis.uni-bamberg.de/handle/uniba/90099},
  language = {deu},
  abstract = {Die Ermöglichung einer effektiven und effizienten Suche nach und in Forschungsdaten ist eine der wesentlichen Zielsetzungen des Forschungsdatenmanagements. Um Suchfunktionalitäten passend nutzen und bereitstellen zu können, sind verschiedene Aspekte des Data Retrieval relevant. Diese reichen vom Verständnis des einer Suche zugrundeliegenden Informationsbedarfs über Modelle zum inhaltsbasierten Ranking von Datensätzen bis hin zu Frameworks und Beispielsystemen für die Suche. Der vorliegende Beitrag gibt hierzu einen Überblick und eine Einführung.},
  keywords = {Data Retrieval}
}

@inproceedings{jegan2023_59341,
  title = {Integrating Access to Authority Data for Improved Interoperability of Research Data in the Digital Humanities},
  author = {Jegan, Robin and Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  year = {2023},
  pages = {829-836},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-593413},
  url = {https://fis.uni-bamberg.de/handle/uniba/59341},
  language = {eng},
  abstract = {Authority data is used to unambiguously identify persons, organisations and places. In this paper, a means to integrate access to several providers of authority data into data curation processes is described, which facilitates disambiguation of geographic data. Combined access to general datasets, in our case the Gemeinsame Normdatei (GND), as well as highly specialized datasets, here the Memorial Archives, improves the resolution of ambiguities and particularly benefits use cases of the Digital Humanities. The integration is necessary in order to abstract from technical, syntactical and semantic heterogeneity of the providers. Operations such as querying geographic information and receiving enriched data from different data sources are facilitated. An overview of the goals of the system, related projects and authority data providers are presented, as well as details on the implementation and further steps.},
  keywords = {authority file, geographic data, bases data integration}
}

@inproceedings{jegan2023_59235,
  title = {Integrating Access to Authority Data for Improved Interoperability of Research Data in the Digital Humanities},
  author = {Jegan, Robin and Fruth, Leon and Gradl, Tobias and Henrich, Andreas},
  year = {2023},
  booktitle = {Datenbanksysteme für Business, Technologie und Web (BTW 2023) : 06.-10. März 2023 in Dresden, Deutschland},
  pages = {829-836},
  publisher = {Gesellschaft für Informatik e.V.},
  isbn = {978-3-88579-725-8},
  doi = {10.18420/BTW2023-54},
  url = {https://fis.uni-bamberg.de/handle/uniba/59235},
  language = {eng},
  abstract = {Authority data is used to unambiguously identify persons, organisations and places. In this paper, a means to integrate access to several providers of authority data into data curation processes is described, which facilitates disambiguation of geographic data. Combined access to general datasets, in our case the Gemeinsame Normdatei (GND), as well as highly specialized datasets, here the Memorial Archives, improves the resolution of ambiguities and particularly benefits use cases of the Digital Humanities. The integration is necessary in order to abstract from technical, syntactical and semantic heterogeneity of the providers. Operations such as querying geographic information and receiving enriched data from different data sources are facilitated. An overview of the goals of the system, related projects and authority data providers are presented, as well as details on the implementation and further steps.},
  keywords = {authority file, geographic data, bases data integration}
}

@incollection{fichtner2021_51561,
  title = {Tafelmalerei Digital und FAIR},
  author = {Fichtner, Mark and Gradl, Tobias and Hastik, Canan},
  year = {2021},
  pages = {35-52},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  doi = {10.20378/irb-51561},
  urn = {urn:nbn:de:bvb:473-irb-515612},
  url = {https://fis.uni-bamberg.de/handle/uniba/51561},
  language = {deu},
  abstract = {Das Germanische Nationalmuseum (GNM) vereint als größtes kulturgeschichtliches Museum des deutschen Sprachraums vielfältige Sammlungen und Archive, das Institut für Kunsttechnologie und Konservierung sowie die größte öffentlich zugängliche Spezialbibliothek für die deutsche Kulturgeschichte. Neben der Grundlagenforschung am Objektbestand widmet sich das Museum innovativer Tiefenforschung zusammen mit universitären und außeruniversitären Partnern im Rahmen von Drittmittelprojekten. Bei Projektbeginn wird auf dem bereits erfassten Datenbestand aufgebaut und dieser im anschließenden Forschungsprozess verfeinert. Am Ende eines Forschungsprojektes fließen die Ergebnisse zurück in den Objektkatalog und aktualisieren die Erkenntnisse aus der Grundlagenforschung oder reichern sie an. Doch nicht alle Ergebnisse aus den Forschungsprojekten können in dem Objektkatalog verzeichnet werden. Gleichzeitig fordern Drittmittelgeber eine Bereitstellung der Forschungsprimärdaten, so dass diese in einem dezidierten Forschungsdatenkorpus gesammelt und zugänglich gemacht werden. Ein dezentraler und
verteilter Zugang auf den Museumsgesamtbestand entspricht jedoch nicht den Anforderungen eines zeitgemäßen Forschungsdatenmanagements. Mit dem Ziel, die kooperative digitale Forschung in den Geistes- und Kulturwissenschaften voranzubringen, wurde mit der DARIAH-DE Datenföderationsarchitektur (DFA) eine Infrastruktur für heterogene Forschungsdatensammlungen geschaffen, die mit Hilfe der Data Modelling Environment (DME) und der Collection Registry (CR) die Zentralisierung verteilter Forschungsdatenkorpora unterstützt. Dieser Beitrag eruiert und validiert, ob mit der DFA unterschiedliche Forschungsdatensammlungen am Beispiel der Tafelmalerei gezielt zusammengeführt und somit die Anforderungen an ein zeitgemäßes, an den FAIR-Prinzipien orientiertes Forschungsdatenmanagement erfüllt werden können.},
  keywords = {Digitale Forschungsinfrastrukturen, DARIAH, Wissenschaftliche Kommunikationsifrastruktur WissKI, Integration, Forschungsdatenmanagement, Datenföderationsarchitektur}
}

@techreport{eckart2021_51791,
  title = {CLARIAH-DE Cross-Service Search : Prospects and Benefits of Merging Subject-specific Services},
  author = {Eckart, Thomas and Gradl, Tobias and Jegan, Robin and Margaretha, Eliza and Werthmann, Antonina and Helfer, Felix and Buddenbohm, Stefan},
  year = {2021},
  publisher = {Niedersächsische Staats- und Universitätsbibliothek Göttingen},
  address = {Göttingen},
  series = {DARIAH-DE working papers},
  urn = {urn:nbn:de:gbv:7-dariah-2021-1-9},
  url = {https://fis.uni-bamberg.de/handle/uniba/51791},
  language = {eng}
}

@techreport{eckart2021_51559,
  title = {CLARIAH-DE Cross-Service Search : Prospects and Benefits of Merging Subject-specific Services},
  author = {Eckart, Thomas and Gradl, Tobias and Jegan, Robin and Margaretha, Eliza and Werthmann, Antonina and Helfer, Felix and Buddenbohm, Stefan},
  year = {2021},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  doi = {10.20378/irb-51559},
  urn = {urn:nbn:de:bvb:473-irb-515593},
  url = {https://fis.uni-bamberg.de/handle/uniba/51559},
  language = {eng},
  abstract = {CLARIAH-DE combines services and offerings of CLARIN-D and DARIAH-DE. This includes various search applications which are made directly available to researchers. These search applications are presented in this working paper based on their main characteristics and compared with a focus on possible harmonizations. Opportunities and risks of different forms of technical integration are highlighted. Identified challenges can be explained in particular considering the background of different organizational and technical frameworks as well as highly specific and discipline-dependent requirements. The integration work that has already been carried out and the experiences gained with regard to future work and possible integration of further applications are also discussed. The experiences made in CLARIAH-DE can especially be of interest for other projects in the field of digital research infrastructures},
  keywords = {Digital research infrastructure, search systems, service integration, metadata, CLARIAH-DE, CLARIN, DARIAH}
}

@techreport{gradl2021_51756,
  title = {Nachnutzung Git-basierter Sammlungen im Rahmen der Infrastrukturdienste von CLARIAH-DE},
  author = {Gradl, Tobias and Jegan, Robin},
  year = {2021},
  pages = {1-37},
  publisher = {Niedersächsische Staats- und Universitätsbibliothek Göttingen},
  address = {Göttingen},
  series = {DARIAH-DE working papers},
  urn = {urn:nbn:de:gbv:7-dariah-2021-2-5},
  url = {https://fis.uni-bamberg.de/handle/uniba/51756},
  language = {deu},
  abstract = {Repositorien auf der Basis von Git werden in zunehmendem Maße auch als Speicher von Forschungsdaten verwendet - auch weil sie Funktionalität wie Versionierung und Kollaboration bereits auf Protokollebene berücksichtigen und Anwenderinnen und Anwender durch ansprechende und funktionale Weboberflächen unterstützen. Über standardisierte Schnittstellen ist zudem ein problemloser Zugriff auf die Inhalte der Repositorien sichergestellt. Die vorliegende Anleitung zeigt, wie Git-Repositorien mit Hilfe der Infrastrukturdienste von CLARIAH-DE dokumentiert, modelliert und in eine übergreifende Suche eingebunden werden können. Das gewählte Beispiel zur Integration der Lehrmaterialien von DARIAH Campus in den CLARIAH-DE Tutorial Finder ist dabei übertragbar auf eine Vielzahl von Anwendungsfällen in den Digital Humantities. Die beschriebenen Dienste der Collection Registy, des Data Modeling Environment und der Generic Search können neben den infrastrukturell betriebenen Instanzen auch für die Umsetzung eigener Integrations- und Suchlösungen installiert und betrieben werden.},
  keywords = {Digitale Forschungsinfrastrukturen, Forschungsdatenmanagement, Datenföderationsarchitektur, Anleitung}
}

@techreport{gradl2021_51558,
  title = {Nachnutzung Git-basierter Sammlungen im Rahmen der Infrastrukturdienste von CLARIAH-DE},
  author = {Gradl, Tobias and Jegan, Robin},
  year = {2021},
  pages = {1-37},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  doi = {10.20378/irb-51558},
  urn = {urn:nbn:de:bvb:473-irb-515587},
  url = {https://fis.uni-bamberg.de/handle/uniba/51558},
  language = {deu},
  abstract = {Repositorien auf der Basis von Git werden in zunehmendem Maße auch als Speicher von Forschungsdaten verwendet - auch weil sie Funktionalität wie Versionierung und Kollaboration bereits auf Protokollebene berücksichtigen und Anwenderinnen und Anwender durch ansprechende und funktionale Weboberflächen unterstützen. Über standardisierte Schnittstellen ist zudem ein problemloser Zugriff auf die Inhalte der Repositorien sichergestellt. Die vorliegende Anleitung zeigt, wie Git-Repositorien mit Hilfe der Infrastrukturdienste von CLARIAH-DE dokumentiert, modelliert und in eine übergreifende Suche eingebunden werden können. Das gewählte Beispiel zur Integration der Lehrmaterialien von DARIAH Campus in den CLARIAH-DE Tutorial Finder ist dabei übertragbar auf eine Vielzahl von Anwendungsfällen in den Digital Humantities. Die beschriebenen Dienste der Collection Registy, des Data Modeling Environment und der Generic Search können neben den infrastrukturell betriebenen Instanzen auch für die Umsetzung eigener Integrations- und Suchlösungen installiert und betrieben werden.},
  keywords = {Digitale Forschungsinfrastrukturen, Forschungsdatenmanagement, Datenföderationsarchitektur, Anleitung}
}

@incollection{henrich2021_51560,
  title = {Integration von Forschungsdaten : Wie können Forschungsinfrastrukturen helfen?},
  author = {Henrich, Andreas and Gradl, Tobias},
  year = {2021},
  booktitle = {Innovation in der Bauwirtschaft},
  pages = {749-762},
  publisher = {De Gruyter},
  address = {Berlin, Boston},
  isbn = {978-3-11-053891-5},
  doi = {10.1515/9783110538915-039},
  url = {https://fis.uni-bamberg.de/handle/uniba/51560},
  language = {deu},
  abstract = {-},
  keywords = {Forschungsdaten}
}

@incollection{henrich2021_49405,
  title = {Data Retrieval},
  author = {Henrich, Andreas and Jegan, Robin and Gradl, Tobias},
  year = {2021},
  booktitle = {Praxishandbuch Forschungsdatenmanagement},
  pages = {427-450},
  publisher = {De Gruyter Saur},
  address = {Berlin},
  isbn = {978-3-11-065365-6},
  doi = {10.1515/9783110657807-024},
  url = {https://fis.uni-bamberg.de/handle/uniba/49405},
  language = {deu},
  abstract = {Die Ermöglichung einer effektiven und effizienten Suche nach und in Forschungsdaten ist eine der wesentlichen Zielsetzungen des Forschungsdatenmanagements. Um Suchfunktionalitäten passend nutzen und bereitstellen zu können, sind verschiedene Aspekte des Data Retrieval relevant. Diese reichen vom Verständnis des einer Suche zugrundeliegenden Informationsbedarfs über Modelle zum inhaltsbasierten Ranking von Datensätzen bis hin zu Frameworks und Beispielsystemen für die Suche. Der vorliegende Beitrag gibt hierzu einen Überblick und eine Einführung.},
  keywords = {Data Retrieval}
}

@incollection{fichtner2020_51568,
  title = {Tafelmalerei Digital und FAIR},
  author = {Fichtner, Mark and Gradl, Tobias and Hastik, Canan},
  year = {2020},
  booktitle = {Bilddaten in den Digitalen Geisteswissenschaften},
  pages = {35-52},
  publisher = {Harrassowitz Verlag},
  address = {Wiesbaden},
  isbn = {978-3-447-11460-8},
  doi = {10.13173/9783447114608.035},
  url = {https://fis.uni-bamberg.de/handle/uniba/51568},
  language = {deu},
  abstract = {Das Germanische Nationalmuseum (GNM) vereint als größtes kulturgeschichtliches Museum des deutschen Sprachraums vielfältige Sammlungen und Archive, das Institut für Kunsttechnologie und Konservierung sowie die größte öffentlich zugängliche Spezialbibliothek für die deutsche Kulturgeschichte. Neben der Grundlagenforschung am Objektbestand widmet sich das Museum innovativer Tiefenforschung zusammen mit universitären und außeruniversitären Partnern im Rahmen von Drittmittelprojekten. Bei Projektbeginn wird auf dem bereits erfassten Datenbestand aufgebaut und dieser im anschließenden Forschungsprozess verfeinert. Am Ende eines Forschungsprojektes fließen die Ergebnisse zurück in den Objektkatalog und aktualisieren die Erkenntnisse aus der Grundlagenforschung oder reichern sie an. Doch nicht alle Ergebnisse aus den Forschungsprojekten können in dem Objektkatalog verzeichnet werden. Gleichzeitig fordern Drittmittelgeber eine Bereitstellung der Forschungsprimärdaten, so dass diese in einem dezidierten Forschungsdatenkorpus gesammelt und zugänglich gemacht werden. Ein dezentraler und
verteilter Zugang auf den Museumsgesamtbestand entspricht jedoch nicht den Anforderungen eines zeitgemäßen Forschungsdatenmanagements. Mit dem Ziel, die kooperative digitale Forschung in den Geistes- und Kulturwissenschaften voranzubringen, wurde mit der DARIAH-DE Datenföderationsarchitektur (DFA) eine Infrastruktur für heterogene Forschungsdatensammlungen geschaffen, die mit Hilfe der Data Modelling Environment (DME) und der Collection Registry (CR) die Zentralisierung verteilter Forschungsdatenkorpora unterstützt. Dieser Beitrag eruiert und validiert, ob mit der DFA unterschiedliche Forschungsdatensammlungen am Beispiel der Tafelmalerei gezielt zusammengeführt und somit die Anforderungen an ein zeitgemäßes, an den FAIR-Prinzipien orientiertes Forschungsdatenmanagement erfüllt werden können.},
  keywords = {Digitale Forschungsinfrastrukturen, DARIAH, Wissenschaftliche Kommunikationsifrastruktur WissKI, Integration, Forschungsdatenmanagement, Datenföderationsarchitektur}
}

@inproceedings{jegan2020_47806,
  title = {Anforderungen an das Forschungsdatenmanagement an einer mittelgroßen Universität und Konzeption einer prototypischen Lösung},
  author = {Jegan, Robin and Gradl, Tobias and Henrich, Andreas},
  year = {2020},
  booktitle = {DHd 2020 Spielräume : Digital Humanities zwischen Modellierung und Interpretation ; Konferenzabstracts},
  pages = {274-275},
  isbn = {978-3-945437-07-0},
  doi = {10.5281/zenodo.3666690},
  url = {https://fis.uni-bamberg.de/handle/uniba/47806},
  language = {deu},
  abstract = {-},
  keywords = {Forschungsdatenmanagement}
}

@incollection{fichtner2019_47115,
  title = {Vom Wandel hin zur objektbasierten Forschung im Kontext von DARIAH-DE},
  author = {Fichtner, Mark and Gradl, Tobias Karl Willi and Hastik, Canan},
  year = {2019},
  booktitle = {Forschungsinfrastrukturen in den digitalen Geisteswissenschaften : wie verändern digitale Infrastrukturen die Praxis der Geisteswissenschaften?},
  pages = {99-110},
  publisher = {CompaRe},
  address = {Frankfurt a. M.},
  urn = {urn:nbn:de:hebis:30:3-519453},
  url = {https://fis.uni-bamberg.de/handle/uniba/47115},
  language = {deu}
}

@techreport{gradl2019_47114,
  title = {Dokumentation der Datenföderationsarchitektur},
  author = {Gradl, Tobias},
  year = {2019},
  address = {Göttingen},
  series = {DARIAH-DE Working Papers},
  urn = {urn:nbn:de:gbv:7-dariah-2019-11-7},
  url = {https://fis.uni-bamberg.de/handle/uniba/47114},
  language = {deu}
}

@inproceedings{steyer2018_45499,
  title = {A research-oriented and case-based data federation for the Humanities : A case study of DARIAH-DE and MWW},
  author = {Steyer, Timo and Gradl, Tobias},
  year = {2018},
  booktitle = {Inaugural conference of the European Association for Digital Humanities (EADH): Proceedings},
  address = {Galway, Ireland},
  doi = {10.5281/zenodo.2536107},
  url = {https://fis.uni-bamberg.de/handle/uniba/45499},
  language = {eng},
  abstract = {MWW stands for three institutions, united by more than 500 years of German and European ideas, literature and culture – and since 2013 by a research association.1 The German Literature Archive Marbach, the Klassik Stiftung Weimar and the Herzog August Library Wolfenbüttel collect, preserve and provide access to sources that are crucial to the study of German literary and intellectual tradition. Thereby they have devoted themselves to the long-term transformation of cultural heritage in Germany. In all three institutions, digitization of their collections has been an important task to build digital collections and provide worldwide access to this cultural heritage. Furthermore, new approaches in the field of digital humanities have been adopted to strengthen the connection of digital collections with the humanities and cultural studies (Schreibmann et al. 2004). All of these goals can be reached easier by cooperation and the use of established tools and infrastructure, which will be demonstrated, based on the example of the implementation of a generic search over collections of all three institutions. For the implementation of the generic search the Data Federation Architecture (DFA) from DARIAH-DE is used.},
  keywords = {Digital Humanities, Data Modelling, Information Retrieval}
}

@inproceedings{mache2018_45485,
  title = {Gute Forschungsdaten, bessere Forschung: wie Forschung durch Forschungsdatenmanagement unterstützt wird},
  author = {Mache, Beata and Trippel, Thorsten and Effinger, Maria and Gradl, Tobias and Haaf, Susanne and Hinrichs, Erhard and Horstmann, Wolfram and Müller, Lydia and Schrade, Thorsten and Teich, Elke},
  editor = {Vogeler, Georg},
  year = {2018},
  booktitle = {DHd 2018 : Kritik der digitalen Vernunft : Konferenzabstracts : Universität zu Köln, 26. Februar bis 2. März 2018},
  pages = {94-98},
  publisher = {Universität zu Köln},
  address = {Köln},
  isbn = {978-3-946275-02-2},
  url = {https://fis.uni-bamberg.de/handle/uniba/45485},
  language = {deu},
  keywords = {Digital Humanities, Forschungsdatenmanagement, Forschungsdaten}
}

@inproceedings{romanello2018_45484,
  title = {Ist die DARIAH-DE Forschungsinfrastruktur fit für Daten der realen Welt? Bericht über einen Anwendungsfall mit archäologischen Daten und seine ersten Ergebnisse},
  author = {Romanello, Matteo and Gradl, Tobias},
  editor = {Vogeler, Georg},
  year = {2018},
  booktitle = {DHd 2018 : Kritik der digitalen Vernunft : Konferenzabstracts : Universität zu Köln, 26. Februar bis 2. März 2018},
  pages = {416-421},
  publisher = {Universität zu Köln},
  address = {Köln},
  isbn = {978-3-946275-02-2},
  url = {https://fis.uni-bamberg.de/handle/uniba/45484},
  language = {deu},
  keywords = {Digital Humanities, Forschungsdateninfrastruktur, DARIAH-DE}
}

@inproceedings{aschauer2018_45155,
  title = {Exploring biographies: finding new group members based on significant terms},
  author = {Aschauer, Anna and Gradl, Tobias and Büchler, Marco},
  year = {2018},
  booktitle = {European Association for Digital Humanities (EADH) conference : Proceedings},
  address = {Galway},
  doi = {10.5281/zenodo.2551546},
  url = {https://fis.uni-bamberg.de/handle/uniba/45155},
  language = {eng},
  abstract = {The development of the method is motivated by the need of historian to detect new group members, when working with social or religious (or otherwise defined) groups. Defining the actors, which are crucial for developing particular phenomena, understanding the interconnections between them and their impact is a basal part of the work as a humanist. However, once covered the main group of actors, it can be challenging going above the known circle of biographies and find other possible members, which are not labeled as a group member, but still meet the criteria. The paper describes an exploratory method of finding new group members.},
  keywords = {DARIAH-DE, Unstructured data, Significant terms, Biograhpies}
}

@inproceedings{gradl2017_107007,
  title = {Nutzung und Kombination von Daten aus strukturierten und unstrukturierten Quellen zur Identifikation transnationaler Lebensläufe},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2017},
  booktitle = {DHd 2016 : Modellierung, Vernetzung, Visualisierung : die Digital Humanities als fächerübergreifendes Forschungsparadigma : Konferenzabstracts : Universität Leipzig 7. bis 12. März 2016},
  pages = {261-265},
  publisher = {nisaba Verlag},
  address = {Duisburg},
  edition = {2. überarbeitete und erweiterte Ausgabe},
  isbn = {978-3-941379-06-0},
  doi = {10.5281/zenodo.3679331},
  url = {https://fis.uni-bamberg.de/handle/uniba/107007},
  language = {deu},
  abstract = {-},
  keywords = {transnationale Lebensläufe}
}

@inproceedings{gradl2017_107006,
  title = {Judaica recherchieren : Unterstützung bei der Realisierung forschungsspezifischer Suchlösungen durch die generische Suche von DARIAH-DE},
  author = {Gradl, Tobias and Lordick, Harald and Henrich, Andreas},
  year = {2017},
  booktitle = {DHd 2016 : Modellierung, Vernetzung, Visualisierung : die Digital Humanities als fächerübergreifendes Forschungsparadigma : Konferenzabstracts : Universität Leipzig 7. bis 12. März 2016},
  pages = {230-235},
  publisher = {nisaba Verlag},
  address = {Duisburg},
  edition = {2. überarbeitete und erweiterte Ausgabe},
  isbn = {978-3-941379-06-0},
  doi = {10.5281/zenodo.3679331},
  url = {https://fis.uni-bamberg.de/handle/uniba/107006},
  language = {deu},
  abstract = {-},
  keywords = {Judaica}
}

@inproceedings{gradl2017_43161,
  title = {Explicating knowledge on data models through domain specific languages},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2017},
  booktitle = {Informatik 2017 : 25.- 29. September 2017 Chemnitz, Deutschland, Proceedings},
  pages = {1125-1136},
  address = {Bonn},
  series = {Gesellschaft für Informatik: GI-Edition / Proceedings},
  isbn = {978-3-88579-669-5},
  doi = {10.18420/in2017\_114},
  url = {https://fis.uni-bamberg.de/handle/uniba/43161},
  language = {eng},
  abstract = {Digital artifacts and metadata of the arts and humanities exhibit a wide spectrum of formats, structures and contexts, and hence a high level of heterogeneity. With particular respect of the characteristics of the application domain, we propose a concept on the basis of formal languages, which allows the separation of technical and contextual aspects of data modeling. Based on a developed framework, domain experts explicate knowledge about data in terms of domain specific languages and derived transformation functions. Independent of actual technical aspects of data transformation and integration (e.g. formats, access protocols, schema languages), experts of particular disciplines, collections or research questions can describe and define data models and relations in an extensive, declarative fashion—utilizing custom data models or standards as applicable. As implicit knowledge is continuously explicated within the data models, interpretations external to the generative context of data are facilitated—thereby promoting interoperability.},
  keywords = {digital humanities, descriptive data modeling, language applications, DARIAH}
}

@inproceedings{eckart2017_43127,
  title = {Working towards a Metadata Federation of CLARIN and DARIAH-DE},
  author = {Eckart, Thomas and Gradl, Tobias},
  year = {2017},
  booktitle = {CLARIN Annual Conference 2017},
  address = {Utrecht},
  doi = {10.5281/zenodo.1173604},
  url = {https://fis.uni-bamberg.de/handle/uniba/43127},
  language = {eng},
  abstract = {Over the past years great effort went into the establishment of research infrastructures for the Humanities and Social Sciences. As a result of the diversity of their targeted research fields and communities, miscellaneous infrastructure projects have developed unique solutions for overlapping target groups. This especially holds for describing available resources by structured metadata and providing them to a wider audience in a user-friendly fashion. This paper focuses on recent work to overcome the gap between the metadata infrastructures of CLARIN and the German branch of the DARIAH project, focusing on design decisions made by both projects and preliminary work focusing on the synergetic evolution of both.},
  keywords = {Digital Humantities, Metadata, Infrastructures, CLARIN, DARIAH}
}

@inproceedings{aschauer2017_41926,
  title = {Daten sammeln, modellieren und durchsuchen mit DARIAH-DE},
  author = {Aschauer, Anna and Dogunke, Swantje and Klaffki, Lisa and Schmunk, Stefan and Steyer, Timo and Gradl, Tobias},
  editor = {Stolz, Michael},
  year = {2017},
  booktitle = {DHd 2017 : Digitale Nachhaltigkeit : Konferenzabstracts},
  pages = {22-27},
  publisher = {Zenodo},
  address = {Bern},
  doi = {10.5281/zenodo.582316},
  url = {https://fis.uni-bamberg.de/handle/uniba/41926},
  language = {deu},
  keywords = {Digital Humanities, Modellierung, Workshop, DARIAH-DE}
}

@inproceedings{gradl2016_40999,
  title = {Extending Data Models by Declaratively Specifying Contextual Knowledge},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2016},
  booktitle = {DocEng '16 : Proceedings of the 2016 ACM Symposium on Document Engineering},
  pages = {123-126},
  publisher = {ACM},
  address = {New York, NY, USA},
  isbn = {978-1-4503-4438-8},
  doi = {10.1145/2960811.2967147},
  url = {https://fis.uni-bamberg.de/handle/uniba/40999},
  language = {eng},
  abstract = {The research data landscape of the arts and humanities is characterized by a high degree of heterogeneity. To improve interoperability, recent initiatives and research infrastructures are encouraging the use of standards and best practices. However, custom data models are often considered necessary to exactly reflect the requirements of a particular collection or research project. To address the needs of scholars in the arts and humanities for a composition of research data irrespective of the degree of structuredness and standardization, we propose a concept on the basis of formal languages, which facilitates declarative data modeling by respective domain experts. By identifying and defining grammatical patterns and deriving transformation functions, the structure of data is generated or extended in accordance with the particular context and needs of the domain.},
  keywords = {digital humanities, descriptive data modeling, language applications, DARIAH}
}

@inproceedings{gradl2016_40908,
  title = {Data Integration for the Arts and Humanities : A Language Theoretical Concept},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2016},
  booktitle = {Research and Advanced Technology for Digital Libraries : 20th International Conference on Theory and Practice of Digital Libraries, TPDL 2016, Hannover, Germany, September 5–9, 2016, Proceedings},
  pages = {281-293},
  publisher = {Springer},
  address = {Cham},
  series = {Lecture Notes in Computer Science},
  isbn = {978-3-319-43996-9},
  doi = {10.1007/978-3-319-43997-6\_22},
  url = {https://fis.uni-bamberg.de/handle/uniba/40908},
  language = {eng},
  abstract = {In the context of the arts and humanities, heterogeneity largely corresponds to the variety of disciplines, their research questions and communities. Resulting from the diversity of the application domain, the analysis of overall requirements and the subsequent derivation of appropriate unifying schemata is prevented by the complexity and size of the domain. The approach presented in this paper is based on the hypothesis that data integration problems in the arts and humanities can be solved on the theoretical foundation of formal languages. In applying a theoretically substantiated framework, integrative solutions on the formal basis of language specifications can be tailored to specific and individual research needs—abstracting from reoccurring technical difficulties and leading the focus of domain experts on semantic aspects.},
  keywords = {Data Integration}
}

@article{aurast2016_40762,
  title = {Big Data und Smart Data in den Geisteswissenschaften},
  author = {Aurast, Anna and Gradl, Tobias and Pernes, Stefan and Pielström, Steffen},
  year = {2016},
  journal = {Bibliothek : Forschung und Praxis},
  volume = {40},
  number = {2},
  pages = {200-206},
  publisher = {de Gruyter Saur},
  address = {Berlin ; New York, NY},
  issn = {1865-7648},
  doi = {10.1515/bfp-2016-0033},
  url = {https://fis.uni-bamberg.de/handle/uniba/40762},
  language = {deu},
  abstract = {Die Verbindung von großen Datenbeständen und geeigneten quantitativen Verfahren ermöglicht es, in den Geisteswissenschaften neue Fragestellungen zu formulieren und bereits bekannte Fragestellungen neu zu denken. Im Kontext des Cluster 5 wird die Möglichkeit genutzt, philologisch-kritische und historisch-vergleichende Perspektiven in die Modellierung großer Datenbestände einfließen zu lassen und in weiterer Folge neue, auf geisteswissenschaftliche Fragestellungen zugeschnittene Analysewerkzeuge zu entwickeln. Das beinhaltet auch die Möglichkeit der empirischen Überprüfung theoretischer Vorannahmen und Kategoriebildungen sowie eine Erweiterung und Veränderung der Modi akademischer Wissensproduktion – durch eine solche Modellierung wird schließlich auch eine unmittelbare Anwendbarkeit und Erfahrbarkeit geisteswissenschaftlicher Begrifflichkeiten möglich. Der Beitrag beschreibt zwei in Cluster 5 entwickelte Analysewerkzeuge: Dariah-DKPro-Wrapper, ein Softwarepaket zur automatischen linguistischen Analyse, zugeschnitten insbesondere auf literarische Texte in Buchlänge, sowie Cosmotool, ein Such- und Analysewerkzeug zur Exploration grenzübergreifender Lebensläufe anhand strukturierter und unstrukturierter Datenbestände.}
}

@article{gradl2016_40766,
  title = {Die DARIAH-DE-Föderationsarchitektur : Datenintegration im Spannungsfeld forschungsspezifischer und domänenübergreifender Anforderungen},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2016},
  journal = {Bibliothek : Forschung und Praxis},
  volume = {40},
  number = {2},
  pages = {222-228},
  publisher = {de Gruyter Saur},
  address = {Berlin ; New York, NY},
  issn = {1865-7648},
  doi = {10.1515/bfp-2016-0027},
  url = {https://fis.uni-bamberg.de/handle/uniba/40766},
  language = {deu},
  abstract = {Dieser Beitrag gibt einen Überblick über die Konzepte und Komponenten der DARIAH-DE-Föderationsarchitektur. Nach einer Abgrenzung grundlegender Anforderungen forschungsspezifischer und domänenübergreifender Integration wird zwischen dem Erstellungs- und Verwendungskontext von Forschungsdaten unterschieden und verdeutlicht, wie die Föderationsarchitektur bei deren Modellierung unterstützt. Die Anwendung im Rahmen der generischen Suche zeigt abschließend, wie in dieser Umgebung generische und forschungsspezifische Anfragen unterstützt werden können.},
  keywords = {Forschungsdaten, Integration, Föderation, generische Suche, DARIAH-DE, research data, integration, federation, generic search, DARIAH-DE}
}

@inproceedings{gradl2016_40759,
  title = {Judaica recherchieren : Unterstützung bei der Realisierung forschungsspezifischer Suchlösungen durch die generische Suche von DARIAH-DE},
  author = {Gradl, Tobias and Lordick, Harald and Henrich, Andreas},
  year = {2016},
  booktitle = {DHd 2016 : Modellierung, Vernetzung, Visualisierung : die Digital Humanities als fächerübergreifendes Forschungsparadigma : Konferenzabstracts : Universität Leipzig 7. bis 12. März 2016},
  pages = {132-136},
  publisher = {nisaba Verlag},
  address = {Duisburg},
  isbn = {978-3-941379-05-3},
  url = {https://fis.uni-bamberg.de/handle/uniba/40759},
  language = {deu}
}

@inproceedings{gradl2016_40770,
  title = {Nutzung und Kombination von Daten aus strukturierten und unstrukturierten Quellen zur Identifikation transnationaler Lebensläufe},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2016},
  booktitle = {DHd 2016 : Modellierung, Vernetzung, Visualisierung : die Digital Humanities als fächerübergreifendes Forschungsparadigma : Konferenzabstracts : Universität Leipzig 7. bis 12. März 2016},
  pages = {129-132},
  publisher = {nisaba Verlag},
  address = {Duisburg},
  isbn = {978-3-941379-05-3},
  url = {https://fis.uni-bamberg.de/handle/uniba/40770},
  language = {deu}
}

@article{henrich2015_40769,
  title = {Erforschung der Weltenwanderer : Über die Nutzung der Wikipedia zur Identifikation grenzüberschreitender Lebensläufe},
  author = {Henrich, Andreas and Gradl, Tobias},
  year = {2015},
  journal = {Uni.vers Forschung : das Magazin der Otto-Friedrich-Universität Bamberg},
  number = {Ein Universum des Wissens für alle - Bamberger Perspektiven auf die Wikipedia},
  pages = {46-49},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  issn = {2195-2558},
  url = {https://fis.uni-bamberg.de/handle/uniba/40769},
  language = {deu},
  abstract = {Für die Geschichtswissenschaften können die Datenbestände von Wikipedia und Wikidata wertvoll sein. Dies betrifft etwa die Erforschung von Biografien: War jemand im 19. Jahr-hundert bereits international vernetzt? Die Nationalbiografien geben hierüber mitunter nur unzureichend Auskunft, da die nationale Perspektive überwiegt. Wikipedia und Wikidata liefern wertvolle zusätzliche Informationen. Für die Auswertung der Daten entwickelt die Bamberger Medieninformatik derzeit einen Prototypen, Historiker und Informatiker arbeiten Hand in Hand.},
  keywords = {Wikipedia}
}

@article{gradl2015_40772,
  title = {Heterogene Daten in den Digital Humanities : Eine Architektur zur forschungsorientierten Föderation von Kollektionen},
  author = {Gradl, Tobias and Henrich, Andreas and Plutte, Christoph},
  year = {2015},
  journal = {Zeitschrift für digitale Geisteswissenschaften},
  number = {Sonderband 1, Grenzen und Möglichkeiten der Digital Humanities},
  publisher = {Wolfenbüttel},
  issn = {2510-1366},
  doi = {10.17175/sb001\_020},
  url = {https://fis.uni-bamberg.de/handle/uniba/40772},
  language = {deu},
  abstract = {Traditionelle Ansätze der Datenintegration basieren zumeist auf einer Harmonisierung heterogener Daten im Rahmen einer übergeordneten, integrativen Datenstruktur wie einem globalen Schema oder einer globalen Ontologie. Der vorliegende Beitrag verdeutlicht die Limitationen eines derartigen Harmonisierungsansatzes für den speziellen Kontext der Digital Humanities und zeigt, wie im Rahmen von DARIAH-DE eine forschungsorientierte und fallbasierte Föderation von Daten erreicht werden kann. Mit Hilfe von Collection, Schema und Crosswalk Registry können durch die Registrierung und Assoziation von Kollektionen und darin verwendeten Datenschemata sowohl übergreifende als auch disziplinspezifische Sichten auf Forschungsdaten geschaffen werden.},
  keywords = {Datenintegration, Digital Humanities, Softwaresystem}
}

@mastersthesis{gradl2014_42052,
  title = {Concept and implementation of a rule framework to dynamically transform data and queries for heterogeneous collections},
  author = {Gradl, Tobias},
  year = {2014},
  publisher = {Zenodo},
  address = {Genève},
  doi = {10.5281/zenodo.804889},
  url = {https://fis.uni-bamberg.de/handle/uniba/42052},
  language = {eng},
  keywords = {data federation, data integration, domain specific languages, digital humanities, language theory},
  school = {Otto-Friedrich-Universität Bamberg}
}

@inproceedings{gradl2014_40756,
  title = {A novel approach for a reusable federation of research data within the arts and humanities},
  author = {Gradl, Tobias and Henrich, Andreas},
  year = {2014},
  booktitle = {Digital humanities 2014 : conference abstracts EPFL-UNIL Lausanne, Switzerland 8-12 July 2014},
  pages = {382-384},
  address = {Lausanne},
  doi = {10.5281/zenodo.58210},
  url = {https://fis.uni-bamberg.de/handle/uniba/40756},
  language = {eng},
  abstract = {In distributed systems literature the orthogonal but interdependent characteristics of autonomy, distribution and heterogeneity are used to classify distributed systems. From a holistic perspective on the arts and humanities, collections have evolved over decades or centuries from highly autonomous disciplines and institutions and are widely spread, which resulted in heterogeneous perspectives and data models. Despite its negative notion as data integration problem, the term heterogeneity also symbolizes the diversity of research methodologies within the disciplines of the arts and humanities. Resolving heterogeneity hence implies an abstraction from the specifics that are valuable for focused disciplinary and interdisciplinary research projects.
Our approach presents a novel concept for data federation in the arts and humanities, which focuses the needs of research projects as well as interdisciplinary and broad use-cases. We especially address the reusability of explicated knowledge on correlations between schemata and digital collections and show where domain experts are required to bridge semantic gaps.},
  keywords = {data integration, data federation, digital humanities, research data, DARIAH-DE}
}

@inproceedings{gradl2014_40752,
  title = {Die DARIAH-DE Architektur zur forschungsorientierten Föderation von Kollektionen in den Digital Humanities},
  author = {Gradl, Tobias and Plutte, Christoph and Henrich, Andreas},
  year = {2014},
  pages = {1-8},
  doi = {10.5281/zenodo.57894},
  url = {https://fis.uni-bamberg.de/handle/uniba/40752},
  language = {deu},
  abstract = {In diesem Beitrag stellen wir eine neuartige Föderationsarchitektur vor, die auf eine Erfassung und Fall-basierte Zusammenführung von Forschungsdaten nach den individuellen Bedürfnissen von Forschungsprojekten abzielt. Digitale Sammlungen werden zentral verzeichnet, zur Vermeidung von Informationsverlusten jedoch nicht harmonisiert, sondern in Form von Beziehungen auf Schemaebene assoziiert, wodurch die Verwendung einer dynamisch föderierten Datenbasis in breiten und interdisziplinären, wie auch in fachspezifischen Anwendungskontexten ermöglicht werden kann},
  keywords = {DARIAH-DE Architektur, Digital Humanities}
}

@article{henrich2013_40761,
  title = {DARIAH(-DE): Digital Research Infrastructure for the Arts and Humanities : Concepts and Perspectives},
  author = {Henrich, Andreas and Gradl, Tobias},
  year = {2013},
  journal = {International Journal of Humanities and Arts Computing},
  volume = {7},
  number = {Issue supplement: Convergence, Collaboration, and Creativity Essays from the 2012 Taiwan},
  pages = {47-58},
  publisher = {Edinburgh Univ. Press},
  address = {Edinburgh},
  issn = {1753-8548},
  doi = {10.3366/ijhac.2013.0059},
  url = {https://fis.uni-bamberg.de/handle/uniba/40761},
  language = {eng},
  abstract = {DARIAH (Digital Research Infrastructure for the Arts and Humanities) is part of the European Strategy on Research Infrastructures. Among 38 projects originally on this roadmap, DARIAH is one of two projects addressing social sciences and humanities. According to its self-conception and its political mandate DARIAH has the mission to enhance and support digitally-enabled research across the humanities and arts. DARIAH aims to develop and maintain an infrastructure in support of ICT-based research practices. One main distinguishing aspect of DARIAH is that it is not focusing on one application domain but especially addresses the support of interdisciplinary research in the humanities and arts. The present paper first gives an overview on DARIAH as a whole and then focuses on the important aspect of technical, syntactic and semantic interoperability. Important aspects in this respect are metadata registries and crosswalk definitions allowing for meaningful cross-collection and inter-collection services and analysis.},
  keywords = {research infrastructure, digital humanities, DARIAH, DARIAH-DE}
}

@inproceedings{henrich2011_4813,
  title = {IR-Unterstützung für die Digital Humanities: Problemstellungen und erste Lösungsideen},
  author = {Henrich, Andreas and Gradl, Tobias},
  year = {2011},
  booktitle = {LWA 2011 : Lernen, Wissen, Adaption},
  url = {https://fis.uni-bamberg.de/handle/uniba/4813},
  language = {deu}
}

