Buscar
Resultados de la búsqueda
-
Dataset
DeezyMatch training set for OCR
Optical character recognition (OCR) is the process of automatically transcribing text from images. The presence of OCR-induced errors in digitised text is a common problem in the digital humanities. OCR errors are usually due to the misrecognition of characters, such as "h" recognised as "b", or "c" recognised as "o".... -
Living with Machines
User Collection -
Journal article
Under the Impression: Multispectral Imaging of Lord Frederick Campbell Charter XXI 5
Lord Frederick Campbell Charter 5 is the only surviving English document that still has an authentic, legible, pre-Conquest seal attached to it. The text purports to be a writ of Edward the Confessor (1003x5–1066) granting a slew of rights to Christ Church Cathedral, Canterbury. We examined the writ using multispectral...Hudson, Alison ; Duffy, Christina
multispectral imaging, digital humanities, conservation, seals, early medieval history, writs, and Norman Conquest
-
Abstract
Historic machines from 'prams' to 'Parliament': new avenues for collaborative linguistic research
Research in computational linguistics has made successful attempts at modelling word meaning at scale, but much remains to be done to put these computational models to the test of historical scholarship (see e.g. Beelen et al. 2021). More importantly, a lot of computational research looks at texts in a historical...Ridge, Mia ; Tolfo, Giorgia ; Westerling, Kalle ; Pedrazzini, Nilo ; McGillivray, Barbara
crowdsourcing, computational linguistics, and digital humanities
-
Conference paper (unpublished)
A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching
Recognizing toponyms and resolving them to their real-world referents is required for providing advanced semantic access to textual data. This process is often hindered by the high degree of variation in toponyms. Candidate selection is the task of identifying the potential entities that can be referred to by a toponym... -
Journal article
Can I believe what I see? Data visualisation and trust in the humanities
Questions of trust are increasingly important in relation to data and its use. The authors focus on humanities data and its visualisation, through analysis of their own recent projects with museums, archives and libraries internationally. Their account connects the specifics of hands-on digital humanities work to larger epistemological questions. They...Boyd Davis, Stephen ; Vane, Olivia ; Kräutli, Florian
scepticism, critical design, interdisciplinarity, ethics, digital humanities, interrogability, data visualisation, and GLAM
-
Conference paper (published)
DeezyMatch: A Flexible Deep Learning Approach to Fuzzy String Matching
We present DeezyMatch, a free, open-source software library written in Python for fuzzy string matching and candidate ranking. Its pair classifier supports various deep neural network architectures for training new classifiers and for fine-tuning a pretrained model, which paves the way for transfer learning in fuzzy string matching. This approach...Hosseini, Kasra ; Nanni, Federico ; Coll Ardanuy, Mariona
Natural Language Processing, string matching, toponym matching, machine learning, and digital humanities
-
Dataset
Living Machines atypical animacy dataset
Atypical animacy detection dataset, based on nineteenth-century sentences in English extracted from an open dataset of nineteenth-century books digitized by the British Library (available via https://doi.org/10.21250/db14, British Library Labs, 2014). This dataset contains 598 sentences containing mentions of machines. Each sentence has been annotated according to the animacy and humanness... -
Dataset
Living with Machines alpha and beta Zooniverse 'accident' task data
Data created through crowdsourcing tasks hosted on the Zooniverse platform. Members of the public were asked to look at a selection of articles from 19th century newspapers that mentioned machines and decide if they described an industrial accident. A further task asked participants to transcribe personal, organisational and place names...Zooniverse volunteers
crowdsourcing, digital history, citizen history, Living with Machines, newspapers, and digital humanities
-
Conference paper (unpublished)
Assessing the Impact of OCR Quality on Downstream NLP Tasks
A growing volume of heritage data is being digitized and made available as text via optical character recognition (OCR). Scholars and libraries are increasingly using OCR-generated text for retrieval and analysis. However, the process of creating text through OCR introduces varying degrees of error to the text. The impact of... -
Journal article
Europeana Newspapers: searching digitized historical newspapers from 23 European countries
Europeana Newspapers is a European Commission-funded project which is refining, aggregating and giving researchers online access to historical newspaper content from 23 European libraries. It also offers free, open source tools which individual libraries can use to assess refinement quality and metadata standards in relation to their own digital newspaper...Willems, Marieke ; Atanassova, Rossitza
digitised historic newspapers, 19th-century newspapers, Europeana Newspapers, and digital humanities