@inproceedings{sebbag-etal-2025-adminset,
title = "{A}dmin{S}et and {A}dmin{BERT}: a Dataset and a Pre-trained Language Model to Explore the Unstructured Maze of {F}rench Administrative Documents",
author = "Sebbag, Thomas and
Quiniou, Solen and
Stucky, Nicolas and
Morin, Emmanuel",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.27/",
pages = "392--406",
abstract = "In recent years, Pre-trained Language Models(PLMs) have been widely used to analyze various documents, playing a crucial role in Natural Language Processing (NLP). However, administrative texts have rarely been used in information extraction tasks, even though this resource is available as open data in many countries. Most of these texts contain many specific domain terms. Moreover, especially in France, they are unstructured because many administrations produce them without a standardized framework. Due to this fact, current language models do not process these documents correctly. In this paper, we propose AdminBERT, the first French pre-trained language models for the administrative domain. Since interesting information in such texts corresponds to named entities and the relations between them, we compare this PLM with general domain language models, fine-tuned on the Named Entity Recognition (NER) task applied to administrative texts, as well as to a Large Language Model (LLM) and to a language model with an architecture different from the BERT one. We show that taking advantage of a PLM for French administrative data increases the performance in the administrative and general domains, on these texts. We also release AdminBERT as well as AdminSet, the pre-training corpus of administrative texts in French and the subset AdminSet-NER, the first NER dataset consisting exclusively of administrative texts in French."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sebbag-etal-2025-adminset">
<titleInfo>
<title>AdminSet and AdminBERT: a Dataset and a Pre-trained Language Model to Explore the Unstructured Maze of French Administrative Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Sebbag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solen</namePart>
<namePart type="family">Quiniou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Stucky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Morin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, Pre-trained Language Models(PLMs) have been widely used to analyze various documents, playing a crucial role in Natural Language Processing (NLP). However, administrative texts have rarely been used in information extraction tasks, even though this resource is available as open data in many countries. Most of these texts contain many specific domain terms. Moreover, especially in France, they are unstructured because many administrations produce them without a standardized framework. Due to this fact, current language models do not process these documents correctly. In this paper, we propose AdminBERT, the first French pre-trained language models for the administrative domain. Since interesting information in such texts corresponds to named entities and the relations between them, we compare this PLM with general domain language models, fine-tuned on the Named Entity Recognition (NER) task applied to administrative texts, as well as to a Large Language Model (LLM) and to a language model with an architecture different from the BERT one. We show that taking advantage of a PLM for French administrative data increases the performance in the administrative and general domains, on these texts. We also release AdminBERT as well as AdminSet, the pre-training corpus of administrative texts in French and the subset AdminSet-NER, the first NER dataset consisting exclusively of administrative texts in French.</abstract>
<identifier type="citekey">sebbag-etal-2025-adminset</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.27/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>392</start>
<end>406</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AdminSet and AdminBERT: a Dataset and a Pre-trained Language Model to Explore the Unstructured Maze of French Administrative Documents
%A Sebbag, Thomas
%A Quiniou, Solen
%A Stucky, Nicolas
%A Morin, Emmanuel
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F sebbag-etal-2025-adminset
%X In recent years, Pre-trained Language Models(PLMs) have been widely used to analyze various documents, playing a crucial role in Natural Language Processing (NLP). However, administrative texts have rarely been used in information extraction tasks, even though this resource is available as open data in many countries. Most of these texts contain many specific domain terms. Moreover, especially in France, they are unstructured because many administrations produce them without a standardized framework. Due to this fact, current language models do not process these documents correctly. In this paper, we propose AdminBERT, the first French pre-trained language models for the administrative domain. Since interesting information in such texts corresponds to named entities and the relations between them, we compare this PLM with general domain language models, fine-tuned on the Named Entity Recognition (NER) task applied to administrative texts, as well as to a Large Language Model (LLM) and to a language model with an architecture different from the BERT one. We show that taking advantage of a PLM for French administrative data increases the performance in the administrative and general domains, on these texts. We also release AdminBERT as well as AdminSet, the pre-training corpus of administrative texts in French and the subset AdminSet-NER, the first NER dataset consisting exclusively of administrative texts in French.
%U https://aclanthology.org/2025.coling-main.27/
%P 392-406
Markdown (Informal)
[AdminSet and AdminBERT: a Dataset and a Pre-trained Language Model to Explore the Unstructured Maze of French Administrative Documents](https://aclanthology.org/2025.coling-main.27/) (Sebbag et al., COLING 2025)
ACL