• DARIAH EU
• 2012-2021close
• Open Access close
• Publications close
• Research data close
• Article close
• EU close
• ZENODO close
• INRIA a CCSD electronic archive ser... close

Since the first ESFRI roadmap in 2006, multiple humanities Research Infrastructures (RIs) have been set up all over the European continent, supporting archaeologists (ARIADNE), linguists (CLARIN-ERIC), Holocaust researchers (EHRI), cultural heritage specialists (IPERION-CH) and others. These examples only scratch the surface of the breadth of research communities that have benefited from close cooperation in the European Research Area.While each field developed discipline-specific services over the years, common themes can also be distinguished. All humanities RIs address, in varying degrees, questions around research data management, the use of standards and the desired interoperability of data across disciplinary boundaries.This article sheds light on how cluster project PARTHENOS developed pooled services and shared solutions for its audience of humanities researchers, RI managers and policymakers. In a time where the convergence of existing infrastructure is becoming ever more important – with the construction of a European Open Science Cloud as an audacious, ultimate goal – we hope that our experiences inform future work and provide inspiration on how to exploit synergies in interdisciplinary, transnational, scientific cooperation. This article has been accepted for publication by EUP in the IJHAC: International Journal of Humanities and Arts Computing (https://www.euppublishing.com/loi/ijhac) International audience

D 2.1: Initial plan for communication and dissemination of project results and RI access, including audience/instrument mapping and communications KPIs (M6, to be updated continuously from then on until M 48).

Obtaining high-quality labelled data for training a classifier in a new application domain is often costly. Transfer Learning (a.k.a. “Inductive Transfer”) tries to alleviate these costs by transferring, to the “target” domain of interest, knowledge available from a different “source” domain. In transfer learning the lack of labelled information from the target domain is compensated by the availability at training time of a set of unlabelled examples from the target distribution. Transductive Transfer Learning denotes the transfer learning setting in which the only set of target documents that we are interested in classifying is known and available at training time. Although this definition is indeed in line with Vapnik’s original definition of “transduction”, current terminology in the field is confused. In this article, we discuss how the term “transduction” has been misused in the transfer learning literature, and propose a clarification consistent with the original characterization of this term given by Vapnik. We go on to observe that the above terminology misuse has brought about misleading experimental comparisons, with inductive transfer learning methods that have been incorrectly compared with transductive transfer learning methods. We then, give empirical evidence that the difference in performance between the inductive version and the transductive version of a transfer learning method can indeed be statistically significant (i.e., that knowing at training time the only data one needs to classify indeed gives an advantage). Our clarification allows a reassessment of the field, and of the relative merits of the major, state-of-the-art algorithms for transfer learning in text classification.

Abstract Contemporary discourse points to the central role that heritage plays in the process of enabling groups of various cultural or ethnic background to strengthen their feeling of belonging and sharing in society. Safeguarding heritage is also valued highly in the priorities of the European Commission. As a result, there have been several long-term initiatives involving the digitisation, annotation and cataloguing of tangible cultural heritage in museums and collections. Specifically, for built heritage, a pressing challenge is that historical monuments such as buildings, temples, churches or city fortification infrastructures are hard to document due to their historic palimpsest; spatial transformations, actions of destruction, reuse of material, or continuous urban development that covers traces and changes the formal integrity and identity of a cultural heritage site. The ability to reason about a monument’s form is crucial for efficient documentation and cataloguing. This paper presents a 3D digitisation workflow through the involvement of reality capture technologies for the annotation and structure analysis of built heritage with the use of 3D Convolutional Neural Networks (3D CNNs) for classification purposes. The presented workflow contributes a new approach to the identification of a building’s architectural components (e.g., arch, dome) and to the study of the stylistic influences (e.g., Gothic, Byzantine) of building parts. In doing so this workflow can assist in tracking a building’s history, identifying its construction period and comparing it to other buildings of the same period. This process can contribute to educational and research activities, as well as facilitate the automated classification of datasets in digital repositories for scholarly research in digital humanities.

Published in OA on RESSI (http://www.ressi.ch/) on the 15.02.22. We present here highlights from an enquiry on the innovations in scholarly writing in the Humanities and Social Sciences in the H2020 project OPERAS-P. This article explores the theme of Open Research Data and its role in the emergence of new models of scholarly writing. We examine more closely the obstacles and fostering conditions to the publication of research data, both from a social and a technical perspective. International audience

The objective of this study was to provide the global community of interested scholars with an updated understanding of digital humanities in Spain, in terms of researchers and research centres, disciplines involved and research topics of interest, trends in digital resources development, main funding bodies and the evolution of their investment since the early nineties. One of the characteristics that differentiates this study from previous approaches is the information used to carry out the research. It combines large datasets of publicly available data from trusted sources with a handpicked selection of records grouping information scattered over the Web. Most of the evidence detected by other studies has been numerically confirmed. At the same time, the new metrics and values established constitute a reference base for monitoring the future evolution of the discipline, and thus favour comparisons. Half of the researchers were found to be affiliated to only nine institutions, whereas the other half of them were scattered across 84 locations. Department affiliation showed a varied pattern of the different degrees of specialization in each institution. Although the major historic role played by Philology was confirmed, the rising interest of other areas of the Humanities and Social Science produces a wider picture, which helped to identify five large clusters of research topics, centred on major disciplines. The quantitative analysis of funding, a dimension almost unexplored in the Humanities, proved to be a valuable way to assess the discipline and its historical evolution. In fact, it revealed interesting trends that led to our proposal of a three-phase periodization in the consolidation of digital humanities in Spain. The paper concludes with a set of recommendations regarding how to deal with issues that could harm the future development of this research area and the role that Spanish researchers can play in the international context. The whole dataset analysed in this publication can be downloaded at https://doi.org/10.5281/zenodo.3893546 A part of this dataset has been also analysed for this poster https://doi.org/10.5281/zenodo.4256689

This paper presents an attempt to provide a generic named-entity recognition and disambiguation module (NERD) called entity-fishing as a stable online service that demonstrates the possible delivery of sustainable technical services within DARIAH, the European digital research infrastructure for the arts and humanities. Deployed as part of the national infrastructure Huma-Num in France, this service provides an efficient state-of-the-art implementation coupled with standardised interfaces allowing an easy deployment on a variety of potential digital humanities contexts. Initially developed in the context of the FP9 EU project CENDARI, the software was well received by the user community and continued to be further developed within the H2020 HIRMEOS project where several open access publishers have integrated the service to their collections of published monographs as a means to enhance retrieval and access. entity-fishing implements entity extraction as well as disambiguation against Wikipedia and Wikidata entries. The service is accessible through a REST API which allows easier and seamless integration, language independent and stable convention and a widely used service-oriented architecture (SOA) design. Input and output data are carried out over a query data model with a defined structure providing flexibility to support the processing of partially annotated text or the repartition of text over several queries. The interface implements a variety of functionalities, like language recognition, sentence segmentation and modules for accessing and looking up concepts in the knowledge base. The API itself integrates more advanced contextual parametrisation or ranked outputs, allowing for the resilient integration in various possible use cases. The entity-fishing API has been used as a concrete use case to draft the experimental stand-off proposal, which has been submitted for integration into the TEI guidelines. The representation is also compliant with the Web Annotation Data Model (WADM). In this paper we aim at describing the functionalities of the service as a reference contribution to the subject of web-based NERD services. In this paper, we detail the workflow from input to output and unpack each building box in the processing flow. Besides, with a more academic approach, we provide a transversal schema of the different components taking into account non-functional requirements in order to facilitate the discovery of bottlenecks, hotspots and weaknesses. We also describe the underlying knowledge base, which is set up on the basis of Wikipedia and Wikidata content. We conclude the paper by presenting our solution for the service deployment: how and which the resources where allocated. The service has been in production since Q3 of 2017, and extensively used by the H2020 HIRMEOS partners during the integration with the publishing platforms. International audience

Communicating is a par excellence scholarly primitive, all probably the most universal scholarly activity across disciplines and over time. This, however, does not imply the uniformity of scholarly communication practices. This is especially true for the humanities domain where the need for cultural nuance in many fields, scholarly outputs are usually grounded in regional, national and language-specific communities. But what are the chances and limitations of bibliodiversity and media diversity in everyday scholarly communication practices? How we can communicate research results in ways that truly align with our increasingly digital and diverse research workflows? What are the cases where the evaluation is disconnected to novel forms of research and what are the possibilities for re-harmonization? Considering that the traditional paradigm of article and book publishing still serves as the highest value currency of career-development in Humanities, the stakes are especially high when looking for answers to such questions. The Innovations in Scholarly Communication Work Package of the Horizon2020 project OPERAS-P is conducting an open consultation to get a better understanding about current trends, gaps and community needs in scholarly writing and research evaluation practices. Working closely with the OPERAS infrastructure dedicated to scholarly communication in the SSH domain, we are in the position to directly translate these needs into supporting the development of the relevant OPERAS activities and services. This workshop, organised in coordination with the DiMPO WG, will be centred around the four scholarly primitives of communicating, linking, commenting, and evaluating. We will look how these basic scholarly activities can be supported by novel scholarly communication practices. Workshop format Target audience: scholars in various humanities disciplines from the DARIAH-community. What participants can gain: Shared knowledge of workflows and resources for innovative scholarly communication that are well-grounded in research realities of the Humanities. Participants' needs will be amplified in the European policy debates and will be considered in the development of scholarly communication services provided by OPERAS: Contribution to DARIAH community: Although scholarly communication is an elementary scholarly activity, this topic has not yet been addressed in DARIAH Annual Event workshops. Recommendations will be incorporated into both DARIAHOpen and DARIAH DiMPO outputs, as well as the forthcoming recommendations to Humanities researchers being prepared by the OPERAS Innovations WG. Method: World café with questions addressing various aspects of research publications (writing, linking, commenting, evaluating) in the humanities. The workshop will build upon the versatile experience of the DiMPO and the OPERAS Working Groups covering such techniques as user stories, process collage, thermometers of indicators etc. adapted for this workshop. Outline: Introduction flesh talks (30 mins) Presentation of OPERAS WP 6. Innovation Writing innovations/challenges with special focus on data publications + presentation of the journals JODH and RDJHSS for further discussion in the breakout room Peer review challenges + presentation of Publons to be further discussed in the breakout Presentation of the findings of the OPERAS-P Landscape Study Presentation of The Open Science Career Assessment Matrix to be further discussed in the breakout BREAKOUT discussions (30 mins) Two SSH data journals: JOHD and RDJHSS (Claire and Elisa) Publons (Erzsébet) OS metrics (Maciej and Jadranka) Reporting back, conclusion (20’)