• Research dataclose
• Other research productsclose
• Other ORP type close
• English close
• Digital Humanities and Cultural Heritage close

This spreadsheet was used to carry a user evaluation of two text search systems developed for the Iconclass (www.iconclass.org) classification system.

List of user requirements for the Media Suite created in the context of the CLARIAH Teaching Fellowship project DISCERN (2021-22).

This document is the first version of a set of guidelines to annotate art-historical text for a newly proposed Knowledge Extraction (KE) challenge, namely Art-KE. This version contains the guidelines to annotate art-historical texts for two tasks: 1) Sequence labelling using artistic concepts, 2) Entity resolution using Wikidata, Getty's Art and Architecture Thesaurus and Iconclass.

This special issue explores the developments in the conversation on iconic images in Modern Italy in the fields of art history, film studies and history of photography in Italian cultural studies, concerning the ways in which we perceive and interpret such images in relation to perceptions of 'Italianicity'.

In the photographs of British sisters Agnes and Dora Bulwer taken at the end of the 19th and the beginning of the 20th century, I argue for an early humanist vision of the peasants, children and workers that they photographed on their travels around Italy.

The British photographers Agnes Bulwer (1856– 1940) and her sister Dora Ellinor Bulwer (1864– 1948) left a legacy of circa 1300 photographs and 890 negatives, date from 1890 to 1913, to the British School at Rome. The photographs are principally of landscapes taken in Rome and the surrounding countryside (the Roman Campagna) but also further afield in Italy and abroad. Many include archaeological and natural sites as well as monuments, art works, and homes and gardens in urban or rural scenes. Their landscape photographs offer a perspective that challenged the existing masculine gaze as developed in landscape photography under the colonial project of the British Empire. Unfettered by the archaeologist’s need for ascetic facts, the Bulwers pioneered an unusual vision of landscape, inspired by the progressive international environment of post-Unification Italy. Agnes and Dora Bulwer often photographed women, whether Italian peasants or travelling companions, presenting a social and gendered gaze that helps to reconsider this period in the light of a dawning international humanitarianism. In spite of their photographic legacy, Agnes and Dora Bulwer remain relatively unknown in the growing field of rediscovered early female photographers connected to archaeology or travel photography. This article reveals their work within a cross-cultural, historical and phenomenological analysis, contributing a new chapter to women’s photographic history, to travel and landscape photography and to the history of British photographers working in Italy.

The IPERION HS project funded by the European Commission under Grant n°871034 offers to European users access to high-level scientific facilities in the field of cultural heritage sciences. Three beamlines of SOLEIL are involved in the project (DIFFABS, DISCO and PUMA), , offering a wide range access to analytical tools using X rays or UV-vis wavelength. These beamlines enable direct analysis of cultural heritage objects and works of art, archaeological artefacts, palaeontological and paleo-environmental specimens, as well as microsamples.

In computer science, robustness can be thought of as the ability of a system to handle erroneous or nonstandard input during execution. This thesis studies the robustness of the methods that extract structured information from unstructured documents containing human language texts. Unfortunately, these methods usually suffer from various problems that prevent achieving robustness to the nonstandard inputs encountered during system execution in real-world scenarios. Throughout the thesis, the key components of the information extraction workflow are analyzed and several novel techniques and enhancements that lead to improved robustness of this process are presented. Firstly, a deep learning-based text recognition method, which can be trained almost exclusively using synthetically generated documents, and a novel data augmentation technique, which improves the accuracy of text recognition on low-quality documents, are presented. Moreover, a novel noise-aware training method that encourages neural network models to build a noise-resistant latent representation of the input is introduced. This approach is shown to improve the accuracy of sequence labeling performed on misrecognized and mistyped text. Further improvements in robustness are achieved by applying noisy language modeling to learn a meaningful representation of misrecognized and mistyped natural language tokens. Furthermore, for the restoration of structural information from documents, a holistic table extraction system is presented. It exhibits high recognition accuracy in a scenario, where raw documents are used as input and the target information is contained in tables. Finally, this thesis introduces a novel evaluation method of the table recognition process that works in a scenario, where the exact location of table objects on a page is not available in the ground-truth annotations. Experimental results are presented on optical character recognition, named entity recognition, part-of-speech tagging, syntactic chunking, table recognition, and interpretation, demonstrating the advantages and the utility of the presented approaches. Moreover, the code and the resources from most of the experiments have been made publicly available to facilitate future research on improving the robustness of information extraction systems.

Easily access the downloadable file for each individual case study or other essay published by InsSciDE on Zenodo. Locate other publications stored in InsSciDE or EU Science Diplomacy Alliance website repositories. Learn about printing your own paperback copy of our book via Amazon's print-on-demand service.