Entity Linking for Historical Documents: Challenges and Solutions

Pontes, Elvys Linhares; Cabrera-Diego, Luis Adrián; Moreno, José G.; Boroş, Emanuela; Hamdi, Ahmed; Sidère, Nicolas; Coustaty, Mickaël; Doucet, Antoine

doi:10.1007/978-3-030-64452-9_19

Cited by 8 publications

(5 citation statements)

References 24 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In many cases, entity extraction is performed manually [27]. In other cases, automatic techniques for entity extraction are used [28][29][30]. The main techniques for NER include rule-based approaches, machine-learning-based approaches, and deeplearning approaches [25].…”

Section: Entity Extractionmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

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 This study demonstrates the potential of using NLP and rule-based techniques to extract valuable information from historical documents and to construct genealogical trees.

show abstract

Section: Entity Extractionmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Other works studied the development of features and rules to improve specific-domain NEL (Heino et al 2017) or entity types (Brando et al 2016). Moreover, some studies focused on the effect of problems frequently encountered in historical documents on NEL (Linhares Pontes et al 2020a). They represented the entities in a continuous space and combined them with a neural attention mechanism to analyze context words and candidate entity embeddings to disambiguate mentions in historical documents.…”

Section: Ocr Errors and Named-entity Linkingmentioning

confidence: 99%

In-depth analysis of the impact of OCR errors on named entity recognition and linking

et al. 2022

Self Cite

View full text Add to dashboard Cite

Named entities (NEs) are among the most relevant type of information that can be used to properly index digital documents and thus easily retrieve them. It has long been observed that NEs are key to accessing the contents of digital library portals as they are contained in most user queries. However, most digitized documents are indexed through their optical character recognition (OCRed) version which include numerous errors. Although OCR engines have considerably improved over the last few years, OCR errors still considerably impact document access. Previous works were conducted to evaluate the impact of OCR errors on named entity recognition (NER) and named entity linking (NEL) techniques separately. In this article, we experimented with a variety of OCRed documents with different levels and types of OCR noise to assess in depth the impact of OCR on named entity processing. We provide a deep analysis of OCR errors that impact the performance of NER and NEL. We then present the resulting exhaustive study and subsequent recommendations on the adequate documents, the OCR quality levels, and the post-OCR correction strategies required to perform reliable NER and NEL.

show abstract

“…The most basic form involves performing string matching. However, Levenshtein distance and other fuzzy matching techniques may be more useful as they can still provide helpful information if there is no exact match [33,34]. More recently, similarity measures have been applied to contextualised embeddings rather than the surface form of the mention and entity [35,36,6].…”

Section: Candidate Generationmentioning

confidence: 99%

Evaluating Automated and Hybrid Neural Disambiguation for African Historical Named Entities

Dunn¹,

Suleman²

2022

Artificial Intelligence Research

View full text Add to dashboard Cite

Documents detailing South African history contain ambiguous names. Ambiguous names may be due to people having the same name or the same person being referred to by multiple different names. Thus when searching for or attempting to extract information about a particular person, the name used may affect the results. This problem may be alleviated by using a Named Entity Disambiguation (NED) system to disambiguate names by linking them to a knowledge base. In recent years, transformer-based language models have led to improvements in NED systems. Furthermore, multilingual language models have shown the ability to learn concepts across languages, reducing the amount of training data required in low-resource languages. Thus a multilingual language model-based NED system was developed to disambiguate people's names within a historical South African context using documents written in English and isiZulu from the 500 Year Archive (FHYA). The multilingual language model-based system substantially improved on a probabilitybased baseline and achieved a micro F1-score of 0.726. At the same time, the entity linking component was able to link 81.9% of the mentions to the correct entity. However, the system's performance on documents written in isiZulu was significantly lower than on the documents written in English. Thus the system was augmented with handcrafted rules to improve its performance. The addition of handcrafted rules resulted in a small but significant improvement in performance when compared to the unaugmented NED system.

show abstract

Entity Linking for Historical Documents: Challenges and Solutions

Cited by 8 publications

References 24 publications

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

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

In-depth analysis of the impact of OCR errors on named entity recognition and linking

Evaluating Automated and Hybrid Neural Disambiguation for African Historical Named Entities

Contact Info

Product

Resources

About