@inproceedings{verkijk-vossen-2022-efficiently,
title = "Efficiently and Thoroughly Anonymizing a Transformer Language Model for {D}utch Electronic Health Records: a Two-Step Method",
author = "Verkijk, Stella and
Vossen, Piek",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.118",
pages = "1098--1103",
abstract = "Neural Network (NN) architectures are used more and more to model large amounts of data, such as text data available online. Transformer-based NN architectures have shown to be very useful for language modelling. Although many researchers study how such Language Models (LMs) work, not much attention has been paid to the privacy risks of training LMs on large amounts of data and publishing them online. This paper presents a new method for anonymizing a language model by presenting the way in which MedRoBERTa.nl, a Dutch language model for hospital notes, was anonymized. The two-step method involves i) automatic anonymization of the training data and ii) semi-automatic anonymization of the LM{'}s vocabulary. Adopting the fill-mask task where the model predicts what tokens are most probable in a certain context, it was tested how often the model will predict a name in a context where a name should be. It was shown that it predicts a name-like token 0.2{\%} of the time. Any name-like token that was predicted was never the name originally present in the training data. By explaining how a LM trained on highly private real-world medical data can be published, we hope that more language resources will be published openly and responsibly so the scientific community can profit from them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verkijk-vossen-2022-efficiently">
<titleInfo>
<title>Efficiently and Thoroughly Anonymizing a Transformer Language Model for Dutch Electronic Health Records: a Two-Step Method</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Verkijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Network (NN) architectures are used more and more to model large amounts of data, such as text data available online. Transformer-based NN architectures have shown to be very useful for language modelling. Although many researchers study how such Language Models (LMs) work, not much attention has been paid to the privacy risks of training LMs on large amounts of data and publishing them online. This paper presents a new method for anonymizing a language model by presenting the way in which MedRoBERTa.nl, a Dutch language model for hospital notes, was anonymized. The two-step method involves i) automatic anonymization of the training data and ii) semi-automatic anonymization of the LM’s vocabulary. Adopting the fill-mask task where the model predicts what tokens are most probable in a certain context, it was tested how often the model will predict a name in a context where a name should be. It was shown that it predicts a name-like token 0.2% of the time. Any name-like token that was predicted was never the name originally present in the training data. By explaining how a LM trained on highly private real-world medical data can be published, we hope that more language resources will be published openly and responsibly so the scientific community can profit from them.</abstract>
<identifier type="citekey">verkijk-vossen-2022-efficiently</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.118</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1098</start>
<end>1103</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficiently and Thoroughly Anonymizing a Transformer Language Model for Dutch Electronic Health Records: a Two-Step Method
%A Verkijk, Stella
%A Vossen, Piek
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F verkijk-vossen-2022-efficiently
%X Neural Network (NN) architectures are used more and more to model large amounts of data, such as text data available online. Transformer-based NN architectures have shown to be very useful for language modelling. Although many researchers study how such Language Models (LMs) work, not much attention has been paid to the privacy risks of training LMs on large amounts of data and publishing them online. This paper presents a new method for anonymizing a language model by presenting the way in which MedRoBERTa.nl, a Dutch language model for hospital notes, was anonymized. The two-step method involves i) automatic anonymization of the training data and ii) semi-automatic anonymization of the LM’s vocabulary. Adopting the fill-mask task where the model predicts what tokens are most probable in a certain context, it was tested how often the model will predict a name in a context where a name should be. It was shown that it predicts a name-like token 0.2% of the time. Any name-like token that was predicted was never the name originally present in the training data. By explaining how a LM trained on highly private real-world medical data can be published, we hope that more language resources will be published openly and responsibly so the scientific community can profit from them.
%U https://aclanthology.org/2022.lrec-1.118
%P 1098-1103
Markdown (Informal)
[Efficiently and Thoroughly Anonymizing a Transformer Language Model for Dutch Electronic Health Records: a Two-Step Method](https://aclanthology.org/2022.lrec-1.118) (Verkijk & Vossen, LREC 2022)
ACL