@inproceedings{vakili-etal-2022-downstream,
title = "Downstream Task Performance of {BERT} Models Pre-Trained Using Automatically De-Identified Clinical Data",
author = "Vakili, Thomas and
Lamproudis, Anastasios and
Henriksson, Aron and
Dalianis, Hercules",
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-1.451",
pages = "4245--4252",
abstract = "Automatic de-identification is a cost-effective and straightforward way of removing large amounts of personally identifiable information from large and sensitive corpora. However, these systems also introduce errors into datasets due to their imperfect precision. These corruptions of the data may negatively impact the utility of the de-identified dataset. This paper de-identifies a very large clinical corpus in Swedish either by removing entire sentences containing sensitive data or by replacing sensitive words with realistic surrogates. These two datasets are used to perform domain adaptation of a general Swedish BERT model. The impact of the de-identification techniques is assessed by training and evaluating the models using six clinical downstream tasks. The results are then compared to a similar BERT model domain-adapted using an unaltered version of the clinical corpus. The results show that using an automatically de-identified corpus for domain adaptation does not negatively impact downstream performance. We argue that automatic de-identification is an efficient way of reducing the privacy risks of domain-adapted models and that the models created in this paper should be safe to distribute to other academic researchers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vakili-etal-2022-downstream">
<titleInfo>
<title>Downstream Task Performance of BERT Models Pre-Trained Using Automatically De-Identified Clinical Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Vakili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasios</namePart>
<namePart type="family">Lamproudis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aron</namePart>
<namePart type="family">Henriksson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hercules</namePart>
<namePart type="family">Dalianis</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>Automatic de-identification is a cost-effective and straightforward way of removing large amounts of personally identifiable information from large and sensitive corpora. However, these systems also introduce errors into datasets due to their imperfect precision. These corruptions of the data may negatively impact the utility of the de-identified dataset. This paper de-identifies a very large clinical corpus in Swedish either by removing entire sentences containing sensitive data or by replacing sensitive words with realistic surrogates. These two datasets are used to perform domain adaptation of a general Swedish BERT model. The impact of the de-identification techniques is assessed by training and evaluating the models using six clinical downstream tasks. The results are then compared to a similar BERT model domain-adapted using an unaltered version of the clinical corpus. The results show that using an automatically de-identified corpus for domain adaptation does not negatively impact downstream performance. We argue that automatic de-identification is an efficient way of reducing the privacy risks of domain-adapted models and that the models created in this paper should be safe to distribute to other academic researchers.</abstract>
<identifier type="citekey">vakili-etal-2022-downstream</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.451</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4245</start>
<end>4252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Downstream Task Performance of BERT Models Pre-Trained Using Automatically De-Identified Clinical Data
%A Vakili, Thomas
%A Lamproudis, Anastasios
%A Henriksson, Aron
%A Dalianis, Hercules
%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 vakili-etal-2022-downstream
%X Automatic de-identification is a cost-effective and straightforward way of removing large amounts of personally identifiable information from large and sensitive corpora. However, these systems also introduce errors into datasets due to their imperfect precision. These corruptions of the data may negatively impact the utility of the de-identified dataset. This paper de-identifies a very large clinical corpus in Swedish either by removing entire sentences containing sensitive data or by replacing sensitive words with realistic surrogates. These two datasets are used to perform domain adaptation of a general Swedish BERT model. The impact of the de-identification techniques is assessed by training and evaluating the models using six clinical downstream tasks. The results are then compared to a similar BERT model domain-adapted using an unaltered version of the clinical corpus. The results show that using an automatically de-identified corpus for domain adaptation does not negatively impact downstream performance. We argue that automatic de-identification is an efficient way of reducing the privacy risks of domain-adapted models and that the models created in this paper should be safe to distribute to other academic researchers.
%U https://aclanthology.org/2022.lrec-1.451
%P 4245-4252
Markdown (Informal)
[Downstream Task Performance of BERT Models Pre-Trained Using Automatically De-Identified Clinical Data](https://aclanthology.org/2022.lrec-1.451) (Vakili et al., LREC 2022)
ACL