@inproceedings{alves-etal-2024-anonymization,
title = "Anonymization Through Substitution: Words vs Sentences",
author = "Alves, Vasco and
Rolla, Vitor and
Alveira, Jo{\~a}o and
Pissarra, David and
Pereira, Duarte and
Curioso, Isabel and
Carreiro, Andr{\'e} and
Lopes Cardoso, Henrique",
editor = "Habernal, Ivan and
Ghanavati, Sepideh and
Ravichander, Abhilasha and
Jain, Vijayanta and
Thaine, Patricia and
Igamberdiev, Timour and
Mireshghallah, Niloofar and
Feyisetan, Oluwaseyi",
booktitle = "Proceedings of the Fifth Workshop on Privacy in Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.privatenlp-1.9",
pages = "85--90",
abstract = "Anonymization of clinical text is crucial to allow the sharing and disclosure of health records while safeguarding patient privacy. However, automated anonymization processes are still highly limited in healthcare practice, as these systems cannot assure the anonymization of all private information. This paper explores the application of a novel technique that guarantees the removal of all sensitive information through the usage of text embeddings obtained from a de-identified dataset, replacing every word or sentence of a clinical note. We analyze the performance of different embedding techniques and models by evaluating them using recently proposed evaluation metrics. The results demonstrate that sentence replacement is better at keeping relevant medical information untouched, while the word replacement strategy performs better in terms of anonymization sensitivity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alves-etal-2024-anonymization">
<titleInfo>
<title>Anonymization Through Substitution: Words vs Sentences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vasco</namePart>
<namePart type="family">Alves</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">João</namePart>
<namePart type="family">Alveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Pissarra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duarte</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Curioso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Carreiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="family">Lopes Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Privacy in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Habernal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sepideh</namePart>
<namePart type="family">Ghanavati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhilasha</namePart>
<namePart type="family">Ravichander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijayanta</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Thaine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timour</namePart>
<namePart type="family">Igamberdiev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloofar</namePart>
<namePart type="family">Mireshghallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oluwaseyi</namePart>
<namePart type="family">Feyisetan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Anonymization of clinical text is crucial to allow the sharing and disclosure of health records while safeguarding patient privacy. However, automated anonymization processes are still highly limited in healthcare practice, as these systems cannot assure the anonymization of all private information. This paper explores the application of a novel technique that guarantees the removal of all sensitive information through the usage of text embeddings obtained from a de-identified dataset, replacing every word or sentence of a clinical note. We analyze the performance of different embedding techniques and models by evaluating them using recently proposed evaluation metrics. The results demonstrate that sentence replacement is better at keeping relevant medical information untouched, while the word replacement strategy performs better in terms of anonymization sensitivity.</abstract>
<identifier type="citekey">alves-etal-2024-anonymization</identifier>
<location>
<url>https://aclanthology.org/2024.privatenlp-1.9</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>85</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Anonymization Through Substitution: Words vs Sentences
%A Alves, Vasco
%A Rolla, Vitor
%A Alveira, João
%A Pissarra, David
%A Pereira, Duarte
%A Curioso, Isabel
%A Carreiro, André
%A Lopes Cardoso, Henrique
%Y Habernal, Ivan
%Y Ghanavati, Sepideh
%Y Ravichander, Abhilasha
%Y Jain, Vijayanta
%Y Thaine, Patricia
%Y Igamberdiev, Timour
%Y Mireshghallah, Niloofar
%Y Feyisetan, Oluwaseyi
%S Proceedings of the Fifth Workshop on Privacy in Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F alves-etal-2024-anonymization
%X Anonymization of clinical text is crucial to allow the sharing and disclosure of health records while safeguarding patient privacy. However, automated anonymization processes are still highly limited in healthcare practice, as these systems cannot assure the anonymization of all private information. This paper explores the application of a novel technique that guarantees the removal of all sensitive information through the usage of text embeddings obtained from a de-identified dataset, replacing every word or sentence of a clinical note. We analyze the performance of different embedding techniques and models by evaluating them using recently proposed evaluation metrics. The results demonstrate that sentence replacement is better at keeping relevant medical information untouched, while the word replacement strategy performs better in terms of anonymization sensitivity.
%U https://aclanthology.org/2024.privatenlp-1.9
%P 85-90
Markdown (Informal)
[Anonymization Through Substitution: Words vs Sentences](https://aclanthology.org/2024.privatenlp-1.9) (Alves et al., PrivateNLP-WS 2024)
ACL
- Vasco Alves, Vitor Rolla, João Alveira, David Pissarra, Duarte Pereira, Isabel Curioso, André Carreiro, and Henrique Lopes Cardoso. 2024. Anonymization Through Substitution: Words vs Sentences. In Proceedings of the Fifth Workshop on Privacy in Natural Language Processing, pages 85–90, Bangkok, Thailand. Association for Computational Linguistics.