Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Linking Named Entities in Diderot's \textit{Encyclopédie} to Wikidata

Pierre Nugues

TL;DR

The paper presents a project to connect Diderot's XVIIIth-century Encyclopédie entries to Wikidata, focusing on geographic and human entities to enable graph-based analyses of historical knowledge. It describes a thorough annotation workflow that combines digitized ENCCRE data with manual linking, resulting in over 10,300 linked entries and a dataset that includes 2,600 location/human links plus 9,500 geographic entries, published as JSON on GitHub. Through SPARQL-driven analysis, the authors extract geographical contexts, lifespans, and occupations of linked entities, revealing biases toward classical figures and European/Near Eastern locales. The resulting resource supports historic NLP tasks and digital humanities research, with plans to extend coverage to additional encyclopedias and regionalize the dataset for more scalable analyses.

Abstract

Diderot's \textit{Encyclopédie} is a reference work from XVIIIth century in Europe that aimed at collecting the knowledge of its era. \textit{Wikipedia} has the same ambition with a much greater scope. However, the lack of digital connection between the two encyclopedias may hinder their comparison and the study of how knowledge has evolved. A key element of \textit{Wikipedia} is Wikidata that backs the articles with a graph of structured data. In this paper, we describe the annotation of more than 10,300 of the \textit{Encyclopédie} entries with Wikidata identifiers enabling us to connect these entries to the graph. We considered geographic and human entities. The \textit{Encyclopédie} does not contain biographic entries as they mostly appear as subentries of locations. We extracted all the geographic entries and we completely annotated all the entries containing a description of human entities. This represents more than 2,600 links referring to locations or human entities. In addition, we annotated more than 9,500 entries having a geographic content only. We describe the annotation process as well as application examples. This resource is available at https://github.com/pnugues/encyclopedie_1751

Linking Named Entities in Diderot's \textit{Encyclopédie} to Wikidata

TL;DR

The paper presents a project to connect Diderot's XVIIIth-century Encyclopédie entries to Wikidata, focusing on geographic and human entities to enable graph-based analyses of historical knowledge. It describes a thorough annotation workflow that combines digitized ENCCRE data with manual linking, resulting in over 10,300 linked entries and a dataset that includes 2,600 location/human links plus 9,500 geographic entries, published as JSON on GitHub. Through SPARQL-driven analysis, the authors extract geographical contexts, lifespans, and occupations of linked entities, revealing biases toward classical figures and European/Near Eastern locales. The resulting resource supports historic NLP tasks and digital humanities research, with plans to extend coverage to additional encyclopedias and regionalize the dataset for more scalable analyses.

Abstract

Diderot's \textit{Encyclopédie} is a reference work from XVIIIth century in Europe that aimed at collecting the knowledge of its era. \textit{Wikipedia} has the same ambition with a much greater scope. However, the lack of digital connection between the two encyclopedias may hinder their comparison and the study of how knowledge has evolved. A key element of \textit{Wikipedia} is Wikidata that backs the articles with a graph of structured data. In this paper, we describe the annotation of more than 10,300 of the \textit{Encyclopédie} entries with Wikidata identifiers enabling us to connect these entries to the graph. We considered geographic and human entities. The \textit{Encyclopédie} does not contain biographic entries as they mostly appear as subentries of locations. We extracted all the geographic entries and we completely annotated all the entries containing a description of human entities. This represents more than 2,600 links referring to locations or human entities. In addition, we annotated more than 9,500 entries having a geographic content only. We describe the annotation process as well as application examples. This resource is available at https://github.com/pnugues/encyclopedie_1751
Paper Structure (14 sections, 3 figures, 1 table)

This paper contains 14 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Previous Work
  3. Entry Linking and Comparison with Wikipedia.
  4. Linking Entries of the Encyclopédie.
  5. Digitization.
  6. Collection of the Corpus
  7. Entry Structure and Annotation
  8. Manual Annotation.
  9. Human Being Subentries.
  10. Format of the Annotated Dataset
  11. Analyzing the Entities
  12. Future Work and Conclusion
  13. Acknowledgments
  14. Bibliographical References

Figures (3)

  • Figure 1: Frequency histogram of the distribution of entries by length in number of characters
  • Figure 2: Locations of the Encyclopédie headwords where a human being is mentioned
  • Figure 3: Dates of deaths of the people mentioned in the Encyclopédie between -700 and 1700