EDDA-Coordinata: An Annotated Dataset of Historical Geographic Coordinates

2026-02-27

AI Summary

This study addresses the challenge of automatically extracting geographic coordinates from 18th-century historical documents, where expressions vary widely and precision is inconsistent. The authors construct the first high-quality annotated dataset of geographic coordinates in early modern French texts, comprising 4,798 entries from Diderot and d’Alembert’s Encyclopédie. They propose a two-stage model: first, a classifier identifies entries containing coordinates; second, a Transformer-based encoder–decoder and decoder-only architecture extracts and standardizes the coordinates. Evaluated via cross-validation on the Encyclopédie, the method achieves an exact match (EM) score of 86%. It further demonstrates strong cross-lingual and cross-temporal generalization, attaining EM scores of 61% on the 18th-century French Dictionnaire de Trévoux and 77% on the 19th-century English Encyclopædia Britannica.

Technology Category

• Natural Language Processing: Information Extraction
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

This paper introduces a dataset of enriched geographic coordinates retrieved from Diderot and d'Alembert's eighteenth-century Encyclopedie. Automatically recovering geographic coordinates from historical texts is a complex task, as they are expressed in a variety of ways and with varying levels of precision. To improve retrieval of coordinates from similar digitized early modern texts, we have created a gold standard dataset, trained models, published the resulting inferred and normalized coordinate data, and experimented applying these models to new texts. From 74,000 total articles in each of the digitized versions of the Encyclopedie from ARTFL and ENCCRE, we examined 15,278 geographical entries, manually identifying 4,798 containing coordinates, and 10,480 with descriptive but non-numerical references. Leveraging our gold standard annotations, we trained transformer-based models to retrieve and normalize coordinates. The pipeline presented here combines a classifier to identify coordinate-bearing entries and a second model for retrieval, tested across encoder-decoder and decoder architectures. Cross-validation yielded an 86% EM score. On an out-of-domain eighteenth-century Trevoux dictionary (also in French), our fine-tuned model had a 61% EM score, while for the nineteenth-century, 7th edition of the Encyclopaedia Britannica in English, the EM was 77%. These findings highlight the gold standard dataset's usefulness as training data, and our two-step method's cross-lingual, cross-domain generalizability.

Problem

• historical geographic coordinates
• named entity recognition
• geoparsing
• gold standard dataset
• early modern texts

Innovation

• historical geographic coordinates
• gold standard dataset
• transformer-based models
• coordinate normalization
• cross-lingual generalization