1,721,178 research outputs found
An AI-based Approach and Platform for the Preservation and Exploitation of Knowledge on the History of Computing
No full textThere is an urgent need for preserving and making available the knowledge related to the
history of computing, for research and education purposes. This is a peculiar kind of Cultural
Heritage, since it tightly mixes hardware, software, documental and even immaterial heritage.
The interlinks among these items and their context is fundamental to properly understand
them and their role. Advanced AI techniques can support this vision and open unprecedented
opportunities to the researchers, practitioners and hobbyists. We are pursuing these objectives
in a project based the GraphBRAIN platform for Knowledge Graphs management
Digital Libraries as Technological Environments. Collaboration of Work and Future Perspectives
No full textThe nature of libraries has changed rapidly with the advent of technology, so far as to change the very way of understanding the library itself. In this paper we examine the impact that digital technologies have had on library workers, and note that so far technology has only been used to transpose the standard library practices, and that little has been done to fully exploit the new opportunities it introduced. To overcome this situation, we propose a graph-based organization of DL data, based on a technology mixing DBs and ontologies. We also propose a holistic data
schema allowing to store information that is usually neglected by traditional cataloging and description standards used in libraries. This would enable the use of AI techniques that may significantly expand the effectiveness of data processing and may dramatically improve the exploitation possibilities of documents
Reflecting on the Europeana Data Model
No full textThe paper describes some issues arising while using Europeana, and analyzes some features of the Europeana Data Model (EDM), starting from the rationale of the project. Some aspects of the theoretical model, derived mostly from the mapping between the provided Cultural Heritage Object (CHO) and the EDM, prevent useful results in users’ queries. The concept of media type, the multi-layer description and the relation between roles and values are some issues about which we reflected. The aim of Europeana to make records available as Linked Open Data on the Web could require moreover a redefinition of the im-plementation techniques
A Quantitative/Qualitative Approach to {OCR} Error Detection and Correction in Old Newspapers for Corpus-assisted Discourse Studies
Full text linkThe use of OCR software to convert printed characters to
digital text is a fundamental tool within diachronic approaches to Corpus-
assisted discourse Studies because allow researchers to expand their inter-
est by making many texts available and analysable through a computer.
However, OCR software are not totally accurate, and the resulting er-
ror rate compromises their effectiveness. This paper proposes a mixed
qualitative-quantitative approach to OCR error detection and correction
in order to develop a methodology for compiling historical corpora. The
proposed approach consists of three main steps: corpus creation, OCR
detection and correction, and application of the automatic rules. The
rules are implemented in R using a “tidyverse” approach for a better
reproducibility of the experiments
A Relational Unsupervised Approach to Author Identification
No full textIn the last decades speaking and writing habits have changed.
Many works faced the author identification task by exploiting frequencybased
approaches, numeric techniques or writing style analysis. Following
the last approach we propose a technique for author identification
based on First-Order Logic. Specifically, we translate the complex data
represented by natural language text to complex (relational) patterns
that represent the writing style of an author. Then, we model an author
as the result of clustering the relational descriptions associated to the
sentences. The underlying idea is that such a model can express the typical
way in which an author composes the sentences in his writings. So,
if we can map such writing habits from the unknown-author model to
the known-author model, we can conclude that the author is the same.
Preliminary results are promising and the approach seems viable in real
contexts since it does not need a training phase and performs well also
with short texts
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Proceedings of the 2nd Workshop on Artificial Intelligence for Cultural Heritage (IAI4CH 2023) co-located with the 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023), Roma, Italy, November 6, 2023
No full textIn 2022, the AI*IA Steering Board approved the establishment of a Working Group on “Artificial Intelligence for Cultural Heritage.” This workshop represented the first opportunity to gather interested researchers and practitioners and form the working group's initial core. This workshop intends to become a yearly event where the group members will meet to exchange ideas, foster cooperation, and get in touch with the other stakeholders. In this second edition, twelve contributions were presented from different research groups in the Italian territory
Linking Historical Evidence to Digital Maps: The MICOLL Map
Full text linkThis paper introduces the MICOLL Map, a digital historical map which is currently under construction by the ERC-funded project MICOLL: Migrating Commercial Law and Language: Rethinking Lex Mercatoria (11th-17th Centuries). The eventual aim of the map is to display the changing routes by which goods and information circulated in the late Middle Ages and the early modern period, with an initial focus on Northern Italy, Southern Germany, and Trans-Alpine exchange. The paper will firstly survey existing digital historical mapping tools before explaining how the MICOLL Map aims to go beyond the current state of the art in a number of ways, chiefly through the promotion of source transparency which will enable the map to be used as a source by professional historians. The second half of the paper will outline the current technical solutions in place to achieve this
- …
