• DARIAH EU
• Publications close
• Article close
• European Commission close
• IT close
• PL close

What makes our idea effective, rewarding and useful? This was the question addressed during a workshop session Digital humanities, citizen science and the arts: synergies towards innovative formats at the COESO project conference entitled Connect. Collaborate.Create (18-21 October 2023 in Paris). The session was an opportunity to present the assumptions of the OPERAS Innovation Lab and the methods it wants to develop in the area of evaluating innovative projects.

The aim of this poster is to provide an overview of the work carried out in the CLS INFRA project and its conclusions for the field of Computational Literary Studies.

L’articolo racconta l’esperienza del D4GNA - Dataset per il Geoportale Nazionale dell’Archeologia nato nell’ambito del progetto ARIADNEplus (Advanced Research Infrastructure for Archaeological Dataset Networking in Europe - plus), conclusosi lo scorso 31 dicembre. Il contributo parte dal contesto più ampio del progetto europeo per addentrarsi nel mondo dei dati archeologici italiani; la soluzione tecnologica, la standardizzazione, la dematerializzazione e la condivisione in rete dei dati sono i temi toccati in questo percorso che ci illustra il procedere verso un obiettivo virtuoso: il Geoportale Nazionale per l’Archeologia (GNA). Il GNA, realizzato dall’Istituto Centrale per l’Archeologia (ICA) e che sarà in rete dal 10 luglio 2023, è il punto di accesso nazionale per accogliere e consultare gli interventi archeologici svolti sotto la direzione scientifica del Ministero della Cultura (MiC), le indagini archeologiche condotte da università e altri enti di ricerca, nonché altre banche dati territoriali.

Digital archives of memory institutions are typically concerned with the cataloguing of artefacts of artistic, historical, and cultural value. Recently, new forms of citizen participation in cultural heritage have emerged, producing a wealth of material spanning from visitors' experiential feedback on exhibitions and cultural artefacts, to digitally mediated interactions like the ones happening on social media platforms. Citizen curation is proposed in the context of the European project SPICE - Social Participation, Cohesion, and Inclusion through Cultural Engagement - as a methodology for producing, collecting, interpreting, and archiving people's responses to cultural objects, with the aim of favouring the emergence of multiple, sometimes conflicting viewpoints, and motivating users and memory institutions to reflect upon them. We argue that citizen curation urges to rethink the nature of computational infrastructures supporting data management of memory institutions, bringing novel challenges that include issues of distribution, authoritativeness, interdependence, privacy, and rights management. To approach these issues, we survey relevant literature towards a distributed, Linked Data infrastructure, with a focus on identifying the roles and requirements involved in such an infrastructure. We show how existing research can contribute significantly in facing the challenges raised by citizen curation, and discuss challenges and opportunities from the socio-technical standpoint.

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

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.