Genealogical Data Mining from Historical Archives: The Case of the Jewish Community in Pisa

Abstract

The Jewish community archive in Pisa owns a vast collection of documents and manuscripts that date back centuries. These documents contain valuable genealogical information, including birth, marriage, and death records. This paper aims to describe the preliminary results of the Archivio Storico della Comunita Ebraica di Pisa (ASCEPI) project, with a focus on the extraction of data from the Nati, Morti e Ballottati (NMB) Registry document in the archive. The NMB Registry contains about 1900 records of births, deaths, and balloted individuals within the Jewish community in Pisa. The study uses a semiautomatic pipeline of digitization, transcription, and Natural Language Processing (NLP) techniques to extract personal data such as names, surnames, birth and death dates, and parental names from each record. The extracted data are then used to build a knowledge base and a genealogical tree for a representative family, Supino. This study demonstrates the potential of using NLP and rule-based techniques to extract valuable information from historical documents and to construct genealogical trees.

Genealogical Data-Driven Visits of Historical Cemeteries

“…This paper improves on the previous work [3], which digitized, transcribed, analyzed, and published some documents from the Historical Archive of the Jewish Community in Pisa over the Web. As an output of the previous work, a preliminary knowledge base was built, containing the entities (person, date, and place) extracted from the Registry of Births and Deaths provided by the Jewish Community.…”

“…Figure 2 shows a sample record in its original version (the manuscript at the top of the figure), the Italian transcription (in the middle), and the English translation (at the bottom). The transcription process from handwritten text to its digital textual representation was described in previous work [3]. In practice, transcription was conducted by domain experts without the usage of any specific tool for transcription.…”

“…The figure shows the text translated into English for convenience, although NER was applied to the original Italian language. Previous work used an approach that combined rule-based and manual correction by a domain expert to extract named entities from a registry of births [3]. This combination of rule-based and manual correction reached an accuracy of about 0.99.…”

“…This human presence made the algorithm particularly slow, making it time-and resource-consuming. This paper applies an LLM-based approach to perform Previous work used an approach that combined rule-based and manual correction by a domain expert to extract named entities from a registry of births [3]. This combination of rule-based and manual correction reached an accuracy of about 0.99.…”