@inproceedings{dermentzi-scheithauer-2024-repurposing,
title = "Repurposing Holocaust-Related Digital Scholarly Editions to Develop Multilingual Domain-Specific Named Entity Recognition Tools",
author = "Dermentzi, Maria and
Scheithauer, Hugo",
editor = "Anuradha, Isuri and
Wynne, Martin and
Frontini, Francesca and
Plum, Alistair",
booktitle = "Proceedings of the First Workshop on Holocaust Testimonies as Language Resources (HTRes) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.htres-1.3",
pages = "18--28",
abstract = "The European Holocaust Research Infrastructure (EHRI) aims to support Holocaust research by making information about dispersed Holocaust material accessible and interconnected through its services. Creating a tool capable of detecting named entities in texts such as Holocaust testimonies or archival descriptions would make it easier to link more material with relevant identifiers in domain-specific controlled vocabularies, semantically enriching it, and making it more discoverable. With this paper, we release EHRI-NER, a multilingual dataset (Czech, German, English, French, Hungarian, Dutch, Polish, Slovak, Yiddish) for Named Entity Recognition (NER) in Holocaust-related texts. EHRI-NER is built by aggregating all the annotated documents in the EHRI Online Editions and converting them to a format suitable for training NER models. We leverage this dataset to fine-tune the multilingual Transformer-based language model XLM-RoBERTa (XLM-R) to determine whether a single model can be trained to recognize entities across different document types and languages. The results of our experiments show that despite our relatively small dataset, in a multilingual experiment setup, the overall F1 score achieved by XLM-R fine-tuned on multilingual annotations is 81.5{\%}. We argue that this score is sufficiently high to consider the next steps towards deploying this model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dermentzi-scheithauer-2024-repurposing">
<titleInfo>
<title>Repurposing Holocaust-Related Digital Scholarly Editions to Develop Multilingual Domain-Specific Named Entity Recognition Tools</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Dermentzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Scheithauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Holocaust Testimonies as Language Resources (HTRes) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isuri</namePart>
<namePart type="family">Anuradha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Wynne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Frontini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The European Holocaust Research Infrastructure (EHRI) aims to support Holocaust research by making information about dispersed Holocaust material accessible and interconnected through its services. Creating a tool capable of detecting named entities in texts such as Holocaust testimonies or archival descriptions would make it easier to link more material with relevant identifiers in domain-specific controlled vocabularies, semantically enriching it, and making it more discoverable. With this paper, we release EHRI-NER, a multilingual dataset (Czech, German, English, French, Hungarian, Dutch, Polish, Slovak, Yiddish) for Named Entity Recognition (NER) in Holocaust-related texts. EHRI-NER is built by aggregating all the annotated documents in the EHRI Online Editions and converting them to a format suitable for training NER models. We leverage this dataset to fine-tune the multilingual Transformer-based language model XLM-RoBERTa (XLM-R) to determine whether a single model can be trained to recognize entities across different document types and languages. The results of our experiments show that despite our relatively small dataset, in a multilingual experiment setup, the overall F1 score achieved by XLM-R fine-tuned on multilingual annotations is 81.5%. We argue that this score is sufficiently high to consider the next steps towards deploying this model.</abstract>
<identifier type="citekey">dermentzi-scheithauer-2024-repurposing</identifier>
<location>
<url>https://aclanthology.org/2024.htres-1.3</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>18</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Repurposing Holocaust-Related Digital Scholarly Editions to Develop Multilingual Domain-Specific Named Entity Recognition Tools
%A Dermentzi, Maria
%A Scheithauer, Hugo
%Y Anuradha, Isuri
%Y Wynne, Martin
%Y Frontini, Francesca
%Y Plum, Alistair
%S Proceedings of the First Workshop on Holocaust Testimonies as Language Resources (HTRes) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F dermentzi-scheithauer-2024-repurposing
%X The European Holocaust Research Infrastructure (EHRI) aims to support Holocaust research by making information about dispersed Holocaust material accessible and interconnected through its services. Creating a tool capable of detecting named entities in texts such as Holocaust testimonies or archival descriptions would make it easier to link more material with relevant identifiers in domain-specific controlled vocabularies, semantically enriching it, and making it more discoverable. With this paper, we release EHRI-NER, a multilingual dataset (Czech, German, English, French, Hungarian, Dutch, Polish, Slovak, Yiddish) for Named Entity Recognition (NER) in Holocaust-related texts. EHRI-NER is built by aggregating all the annotated documents in the EHRI Online Editions and converting them to a format suitable for training NER models. We leverage this dataset to fine-tune the multilingual Transformer-based language model XLM-RoBERTa (XLM-R) to determine whether a single model can be trained to recognize entities across different document types and languages. The results of our experiments show that despite our relatively small dataset, in a multilingual experiment setup, the overall F1 score achieved by XLM-R fine-tuned on multilingual annotations is 81.5%. We argue that this score is sufficiently high to consider the next steps towards deploying this model.
%U https://aclanthology.org/2024.htres-1.3
%P 18-28
Markdown (Informal)
[Repurposing Holocaust-Related Digital Scholarly Editions to Develop Multilingual Domain-Specific Named Entity Recognition Tools](https://aclanthology.org/2024.htres-1.3) (Dermentzi & Scheithauer, htres-WS 2024)
ACL