@inproceedings{viksna-skadina-2025-anonymise,
title = "Anonymise: A Tool for Multilingual Document Pseudonymisation",
author = "V{\={i}}ksna, Rinalds and
Skadina, Inguna",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.154/",
pages = "1327--1332",
abstract = "According to the EU legislation, documents containing personal information need to be anonymized before public sharing. However, manual anonymisation is a time-consuming and costly process. Thus, there is a need for a robust text de-identification technique that accurately identifies and replaces personally identifiable information. This paper introduces the Anonymise tool, a system for document de-identification. The tool accepts text documents of various types (e.g., MS Word, plain-text), de-identifies personal information, and saves the de-identified document in its original format. The tool employs a modular architecture, integrating list-based matching, regular expressions and deep-learning-based named entity recognition to detect spans for redaction. Our evaluation results demonstrate high recall rates, making Anonymise a reliable solution for ensuring no sensitive information is left exposed. The tool can be accessed through a userfriendly web-based interface or API, offering flexibility for both individual and large-scale document processing needs. By automating document de-identification with high accuracy and efficiency, Anonymise presents a reliable solution for ensuring compliance with EU privacy regulations while reducing the time and cost associated with manual anonymisation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="viksna-skadina-2025-anonymise">
<titleInfo>
<title>Anonymise: A Tool for Multilingual Document Pseudonymisation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rinalds</namePart>
<namePart type="family">Vīksna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inguna</namePart>
<namePart type="family">Skadina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>According to the EU legislation, documents containing personal information need to be anonymized before public sharing. However, manual anonymisation is a time-consuming and costly process. Thus, there is a need for a robust text de-identification technique that accurately identifies and replaces personally identifiable information. This paper introduces the Anonymise tool, a system for document de-identification. The tool accepts text documents of various types (e.g., MS Word, plain-text), de-identifies personal information, and saves the de-identified document in its original format. The tool employs a modular architecture, integrating list-based matching, regular expressions and deep-learning-based named entity recognition to detect spans for redaction. Our evaluation results demonstrate high recall rates, making Anonymise a reliable solution for ensuring no sensitive information is left exposed. The tool can be accessed through a userfriendly web-based interface or API, offering flexibility for both individual and large-scale document processing needs. By automating document de-identification with high accuracy and efficiency, Anonymise presents a reliable solution for ensuring compliance with EU privacy regulations while reducing the time and cost associated with manual anonymisation.</abstract>
<identifier type="citekey">viksna-skadina-2025-anonymise</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.154/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1327</start>
<end>1332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Anonymise: A Tool for Multilingual Document Pseudonymisation
%A Vīksna, Rinalds
%A Skadina, Inguna
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F viksna-skadina-2025-anonymise
%X According to the EU legislation, documents containing personal information need to be anonymized before public sharing. However, manual anonymisation is a time-consuming and costly process. Thus, there is a need for a robust text de-identification technique that accurately identifies and replaces personally identifiable information. This paper introduces the Anonymise tool, a system for document de-identification. The tool accepts text documents of various types (e.g., MS Word, plain-text), de-identifies personal information, and saves the de-identified document in its original format. The tool employs a modular architecture, integrating list-based matching, regular expressions and deep-learning-based named entity recognition to detect spans for redaction. Our evaluation results demonstrate high recall rates, making Anonymise a reliable solution for ensuring no sensitive information is left exposed. The tool can be accessed through a userfriendly web-based interface or API, offering flexibility for both individual and large-scale document processing needs. By automating document de-identification with high accuracy and efficiency, Anonymise presents a reliable solution for ensuring compliance with EU privacy regulations while reducing the time and cost associated with manual anonymisation.
%U https://aclanthology.org/2025.ranlp-1.154/
%P 1327-1332
Markdown (Informal)
[Anonymise: A Tool for Multilingual Document Pseudonymisation](https://aclanthology.org/2025.ranlp-1.154/) (Vīksna & Skadina, RANLP 2025)
ACL
- Rinalds Vīksna and Inguna Skadina. 2025. Anonymise: A Tool for Multilingual Document Pseudonymisation. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1327–1332, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.