Big Data of the Past

Abstract

Big Data is not a new phenomenon. History is punctuated by regimes of data acceleration, characterized by feelings of information overload accompanied by periods of social transformation and the invention of new technologies. During these moments, private organizations, administrative powers, and sometimes isolated individuals have produced important datasets, organized following a logic that is often subsequently superseded but was at the time, nevertheless, coherent. To be translated into relevant sources of information about our past, these document series need to be redocumented using contemporary paradigms. The intellectual, methodological, and technological challenges linked to this translation process are the central subject of this article.

Overview of CLEF HIPE 2020: Named Entity Recognition and Linking on Historical Newspapers

“…Ertim, affiliated with Inalco, Paris, applied their legacy (2010-13) NER system mXS 22 [36] for contemporary texts on the historical French HIPE data without any adaptation or training. The system uses pattern mining and nonneural machine learning for NERC and their model is based on the QUAERO standard [45], which is the basis for the HIPE annotation guidelines.…”

“…Thanks to largescale digitization projects driven by cultural institutions, millions of images are being acquired and, when it comes to text, their content is transcribed, either manually via dedicated interfaces, or automatically via Optical Character Recognition (OCR). Beyond this great achievement in terms of document preservation and accessibility, the next crucial step is to adapt and develop appropriate language technologies to search and retrieve the contents of this 'Big Data from the Past' [22]. In this regard, information extraction techniques, and particularly NE recognition and linking, can certainly be regarded among the first and most crucial processing steps.…”

Big Data and the Little Big Bang: An Epistemological (R)evolution

“…Although the current amount of available information was never experienced before, this was equally veritable in many moments of human history. It is sufficient to think, for example, about the specimen of 17,000 argyle tablets recording administrative data that were produced in the ancient city of Ebla between II and III millennium BC (Kaplan and di Lenardo, 2017), and consider the massive impact that movable type had on the velocity of the printing process and on the volume of printed material during the so-called "printing revolution" of 1,455 (Eisenstein, 1983). So, what makes the current overload so different from the previous ones?…”

Digital Cultural Heritage Meets Digital Humanities

“…Previously disconnected datasets form larger wholes that can be studied using algorithm methods. The articulation between Digital Humanities and Cultural Heritage can be explored in the way skills must be combined to process and interpret these large cultural databases (Kaplan, 2015;Kaplan and Lenardo, 2017). More precisely, Digital Humanities and Cultural Heritage expertise must be combined at crucial interpretative moments: a) During the redocumentation processes, when data from the past systematically undergo a form a regularization to match the paradigm of contemporary information systems and documented and reversible choices are made for massive reinterpretation.…”