@inproceedings{torres-aguilar-2022-multilingual,
title = "Multilingual Named Entity Recognition for Medieval Charters Using Stacked Embeddings and Bert-based Models.",
author = "Torres Aguilar, Sergio",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lt4hala-1.17",
pages = "119--128",
abstract = "In recent years the availability of medieval charter texts has increased thanks to advances in OCR and HTR techniques. But the lack of models that automatically structure the textual output continues to hinder the extraction of large-scale lectures from these historical sources that are among the most important for medieval studies. This paper presents the process of annotating and modelling a corpus to automatically detect named entities in medieval charters in Latin, French and Spanish and address the problem of multilingual writing practices in the Late Middle Ages. It introduces a new annotated multilingual corpus and presents a training pipeline using two approaches: (1) a method using contextual and static embeddings coupled to a Bi-LSTM-CRF classifier; (2) a fine-tuning method using the pre-trained multilingual BERT and RoBERTa models. The experiments described here are based on a corpus encompassing about 2.3M words (7576 charters) coming from five charter collections ranging from the 10th to the 15th centuries. The evaluation proves that both multilingual classifiers based on general purpose models and those specifically designed achieve high-performance results and do not show performance drop compared to their monolingual counterparts. This paper describes the corpus and the annotation guideline, and discusses the issues related to the linguistic of the charters, the multilingual writing practices, so as to interpret the results within a larger historical perspective.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="torres-aguilar-2022-multilingual">
<titleInfo>
<title>Multilingual Named Entity Recognition for Medieval Charters Using Stacked Embeddings and Bert-based Models.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Torres Aguilar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years the availability of medieval charter texts has increased thanks to advances in OCR and HTR techniques. But the lack of models that automatically structure the textual output continues to hinder the extraction of large-scale lectures from these historical sources that are among the most important for medieval studies. This paper presents the process of annotating and modelling a corpus to automatically detect named entities in medieval charters in Latin, French and Spanish and address the problem of multilingual writing practices in the Late Middle Ages. It introduces a new annotated multilingual corpus and presents a training pipeline using two approaches: (1) a method using contextual and static embeddings coupled to a Bi-LSTM-CRF classifier; (2) a fine-tuning method using the pre-trained multilingual BERT and RoBERTa models. The experiments described here are based on a corpus encompassing about 2.3M words (7576 charters) coming from five charter collections ranging from the 10th to the 15th centuries. The evaluation proves that both multilingual classifiers based on general purpose models and those specifically designed achieve high-performance results and do not show performance drop compared to their monolingual counterparts. This paper describes the corpus and the annotation guideline, and discusses the issues related to the linguistic of the charters, the multilingual writing practices, so as to interpret the results within a larger historical perspective.</abstract>
<identifier type="citekey">torres-aguilar-2022-multilingual</identifier>
<location>
<url>https://aclanthology.org/2022.lt4hala-1.17</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>119</start>
<end>128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Named Entity Recognition for Medieval Charters Using Stacked Embeddings and Bert-based Models.
%A Torres Aguilar, Sergio
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F torres-aguilar-2022-multilingual
%X In recent years the availability of medieval charter texts has increased thanks to advances in OCR and HTR techniques. But the lack of models that automatically structure the textual output continues to hinder the extraction of large-scale lectures from these historical sources that are among the most important for medieval studies. This paper presents the process of annotating and modelling a corpus to automatically detect named entities in medieval charters in Latin, French and Spanish and address the problem of multilingual writing practices in the Late Middle Ages. It introduces a new annotated multilingual corpus and presents a training pipeline using two approaches: (1) a method using contextual and static embeddings coupled to a Bi-LSTM-CRF classifier; (2) a fine-tuning method using the pre-trained multilingual BERT and RoBERTa models. The experiments described here are based on a corpus encompassing about 2.3M words (7576 charters) coming from five charter collections ranging from the 10th to the 15th centuries. The evaluation proves that both multilingual classifiers based on general purpose models and those specifically designed achieve high-performance results and do not show performance drop compared to their monolingual counterparts. This paper describes the corpus and the annotation guideline, and discusses the issues related to the linguistic of the charters, the multilingual writing practices, so as to interpret the results within a larger historical perspective.
%U https://aclanthology.org/2022.lt4hala-1.17
%P 119-128
Markdown (Informal)
[Multilingual Named Entity Recognition for Medieval Charters Using Stacked Embeddings and Bert-based Models.](https://aclanthology.org/2022.lt4hala-1.17) (Torres Aguilar, LT4HALA 2022)
ACL