• DARIAH EU
• 2012-2021close
• Open Access close
• ISTI Open Portal close
• Digital Humanities and Cultural Her... close

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.

Among the goals of the ARIADNE project (a digital infrastructure for archaeological documentation), two interrelated objectives are the design of new services (or the integration of existing ones) and the implementation of an intense training & hands-on program. Especially in the case of visual media (which are evolving at an impressing pace) services should be paired by user consultation and training, since a pre-requisite of any service activity is to consolidate knowledge on the potential of new media and the impact those could have in the selected discipline. The latter is the main objective of the TNA training program and of other user consultation events that have been organized in the first 18 months of the ARIADNE project. This short contribution presents the results of this activity and our plans for the design of new services.

Abstract Limited bandwidth is a strong constraint when efficient transmission of 3D data to Web clients and mobile applications is needed. In this paper we present a novel multi-resolution WebGL based rendering algorithm which combines progressive loading, view-dependent resolution and mesh compression, providing high frame rates and a decoding speed of million of triangles per second in JavaScript. The method is parallelizable and scalable to very large models. The algorithm is based on the local multi-resolution approaches provided by the community, but ad-hoc solutions had to be studied and implemented to provide adequate performances. In particular, a compression mechanism that reached very high compression rate without impact on rendering performance was implemented. Moreover, the data partition strategy was modified in order to be able to load different types of data (i.e. point clouds) and better adapt to the potentials and limitations of web-based rendering.

This paper discusses the registry developed by the ARIADNE project for describing the archaeological resources that are made available by the partners of the project for the purposes of discovery, access and integration on a research infrastructure. These resources include: data, services and language resources, such as metadata formats, vocabularies and mappings. The registry is addressed to cultural institutions, private or public, which wish to describe their assets in order to make them known to e-infrastructures.

This deliverable describes the activities carried out during the three editions of the Summer School "Design of Archaeological Datasets", hosted by the partner CNR - ISTI (NeMIS Lab) and reports the results achieved, relying on the feedback given by the students at the end of each edition of the courses. The feedback questionnaires completed by the attendees are reported in appendix. In the EC Surveys all the participants expressed an overall appreciation of the course between "Good" and "Very good". Students globally expressed satisfaction for the scientific contents of the school, appreciating the outlines of the Semantic Web architecture, metadata structure and database design. Most of them declared the course provided a broader and clearer picture of the Information Technology aspects and tools available to design the data collected in archaeological research.

Research e-infrastructures, digital archives and data services have become important pillars of scientific enterprise that in recent decades has become ever more collaborative, distributed and data-intensive. The archaeological research community has been an early adopter of digital tools for data acquisition, organisation, analysis and presentation of research results of individual projects. However, the provision of e-infrastructure and services for data sharing, discovery, access and re-use has lagged behind. This situation is being addressed by ARIADNE: the Advanced Research Infrastructure for Archaeological Dataset Networking in Europe. This EU-funded network has developed an e-infrastructure that enables data providers to register and provide access to their resources (datasets, collections) through the ARIADNE data portal, facilitating discovery, access and other services across the integrated resources. This article describes the current landscape of data repositories and services for archaeologists in Europe, and the issues that make interoperability between them difficult to realise. The results of the ARIADNE surveys on users' expectations and requirements are also presented. The main section of the article describes the architecture of the e-infrastructure, core services (data registration, discovery and access) and various other extant or experimental services. The on-going evaluation of the data integration and services is also discussed. Finally, the article summarises lessons learned, and outlines the prospects for the wider engagement of the archaeological research community in sharing data through ARIADNE. International audience

We present the methodological and technical process we adopted to develop DanteSources, a Web application that allows free access to the knowledge about Dante Alighieri's primary sources, i.e. the works of other authors that Dante cites in his texts. Up to now, this knowledge has been collected in many paper books, making it difficult for the scholars to retrieve it and to produce a complete overview of these data. Using Semantic Web technologies, we developed an ontology expressed in the Resource Description Framework Schema vocabulary providing the terms to represent this knowledge in a machine-readable form. A semi-automatic tool helps the scholars to populate the ontology with the data included in authoritative paper commentaries to Dante's works. Then, the tool automatically saves the resulting Resource Description Framework graph in a triple store. On top of this graph, we developed DanteSources, a Web application that allows users to extract and display the information stored in the knowledge base in the form of charts and tables. Finally, we report the results of a survey to collect suggestions from end-users on their interactions with DanteSources. The methodology and the tools we developed are easily reusable, e.g. to represent the knowledge about primary sources of other authors of the Italian and the international literature.

Abstract. The remote visualization and navigation of 3D data directly inside the web browser is becoming a viable option, due to the recent efforts in standardizing the components for 3D rendering on the web platform. Nevertheless, handling complex models may be a challenge, especially when a more generic solution is needed to handle different cases. In particular, archeological and architectural models are usually hard to handle, since their navigation can be managed in several ways, and a completely free navigation may be misleading and not realistic. In this paper we present a solution for the remote navigation of these dataset in a WebGL component. The navigation has two possible modes: the ”bird’s eye” mode, where the user is able to see the model from above, and the ”first person” mode, where the user can move inside the structure. The two modalities are linked by a point of interest, that helps the user to control the navigation in an intuitive fashion. Since the terrain may not be flat, and the architecture may be complex, it’s necessary to handle these issues, possibly without implementing complex mesh-based collision mechanisms. Hence, a complete navigation is obtained by storing the height and collision information in an image, which provides a very simple source of data. Moreover, the same image-based approach can be used to store additional information that could enhance the navigation experience. The method has been tested in two complex test cases, showing that a simple yet powerful interaction can be obtained with limited pre-processing of data.