@inproceedings{ribeiro-etal-2023-incognitus,
title = "{INCOGNITUS}: A Toolbox for Automated Clinical Notes Anonymization",
author = "Ribeiro, Bruno and
Rolla, Vitor and
Santos, Ricardo",
editor = "Croce, Danilo and
Soldaini, Luca",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-demo.22/",
doi = "10.18653/v1/2023.eacl-demo.22",
pages = "187--194",
abstract = "Automated text anonymization is a classical problem in Natural Language Processing (NLP). The topic has evolved immensely throughout the years, with the first list-search and rule-based solutions evolving to statistical modeling approaches and later to advanced systems that rely on powerful state-of-the-art language models. Even so, these solutions fail to be widely implemented in the most privacy-demanding areas of activity, such as healthcare; none of them is perfect, and most can not guarantee rigorous anonymization. This paper presents INCOGNITUS, a flexible platform for the automated anonymization of clinical notes that offers the possibility of applying different techniques. The available tools include an underexplored yet promising method that guarantees 100{\%} recall by replacing each word with a semantically identical one. In addition, the presented framework incorporates a performance evaluation module to compute a novel metric for information loss assessment in real-time."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ribeiro-etal-2023-incognitus">
<titleInfo>
<title>INCOGNITUS: A Toolbox for Automated Clinical Notes Anonymization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitor</namePart>
<namePart type="family">Rolla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Croce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Soldaini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated text anonymization is a classical problem in Natural Language Processing (NLP). The topic has evolved immensely throughout the years, with the first list-search and rule-based solutions evolving to statistical modeling approaches and later to advanced systems that rely on powerful state-of-the-art language models. Even so, these solutions fail to be widely implemented in the most privacy-demanding areas of activity, such as healthcare; none of them is perfect, and most can not guarantee rigorous anonymization. This paper presents INCOGNITUS, a flexible platform for the automated anonymization of clinical notes that offers the possibility of applying different techniques. The available tools include an underexplored yet promising method that guarantees 100% recall by replacing each word with a semantically identical one. In addition, the presented framework incorporates a performance evaluation module to compute a novel metric for information loss assessment in real-time.</abstract>
<identifier type="citekey">ribeiro-etal-2023-incognitus</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-demo.22</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-demo.22/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>187</start>
<end>194</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T INCOGNITUS: A Toolbox for Automated Clinical Notes Anonymization
%A Ribeiro, Bruno
%A Rolla, Vitor
%A Santos, Ricardo
%Y Croce, Danilo
%Y Soldaini, Luca
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F ribeiro-etal-2023-incognitus
%X Automated text anonymization is a classical problem in Natural Language Processing (NLP). The topic has evolved immensely throughout the years, with the first list-search and rule-based solutions evolving to statistical modeling approaches and later to advanced systems that rely on powerful state-of-the-art language models. Even so, these solutions fail to be widely implemented in the most privacy-demanding areas of activity, such as healthcare; none of them is perfect, and most can not guarantee rigorous anonymization. This paper presents INCOGNITUS, a flexible platform for the automated anonymization of clinical notes that offers the possibility of applying different techniques. The available tools include an underexplored yet promising method that guarantees 100% recall by replacing each word with a semantically identical one. In addition, the presented framework incorporates a performance evaluation module to compute a novel metric for information loss assessment in real-time.
%R 10.18653/v1/2023.eacl-demo.22
%U https://aclanthology.org/2023.eacl-demo.22/
%U https://doi.org/10.18653/v1/2023.eacl-demo.22
%P 187-194
Markdown (Informal)
[INCOGNITUS: A Toolbox for Automated Clinical Notes Anonymization](https://aclanthology.org/2023.eacl-demo.22/) (Ribeiro et al., EACL 2023)
ACL
- Bruno Ribeiro, Vitor Rolla, and Ricardo Santos. 2023. INCOGNITUS: A Toolbox for Automated Clinical Notes Anonymization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 187–194, Dubrovnik, Croatia. Association for Computational Linguistics.