@inproceedings{lothritz-etal-2023-evaluating,
title = "Evaluating the Impact of Text De-Identification on Downstream {NLP} Tasks",
author = "Lothritz, Cedric and
Lebichot, Bertrand and
Allix, Kevin and
Ezzini, Saad and
Bissyand{\'e}, Tegawend{\'e} and
Klein, Jacques and
Boytsov, Andrey and
Lefebvre, Cl{\'e}ment and
Goujon, Anne",
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.2",
pages = "10--16",
abstract = "Data anonymisation is often required to comply with regulations when transfering information across departments or entities. However, the risk is that this procedure can distort the data and jeopardise the models built on it. Intuitively, the process of training an NLP model on anonymised data may lower the performance of the resulting model when compared to a model trained on non-anonymised data. In this paper, we investigate the impact of de-identification on the performance of nine downstream NLP tasks. We focus on the anonymisation and pseudonymisation of personal names and compare six different anonymisation strategies for two state-of-the-art pre-trained models. Based on these experiments, we formulate recommendations on how the de-identification should be performed to guarantee accurate NLP models. Our results reveal that de-identification does have a negative impact on the performance of NLP models, but this impact is relatively low. We also find that using pseudonymisation techniques involving random names leads to better performance across most tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lothritz-etal-2023-evaluating">
<titleInfo>
<title>Evaluating the Impact of Text De-Identification on Downstream NLP Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cedric</namePart>
<namePart type="family">Lothritz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertrand</namePart>
<namePart type="family">Lebichot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Allix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tegawendé</namePart>
<namePart type="family">Bissyandé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacques</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Boytsov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clément</namePart>
<namePart type="family">Lefebvre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Goujon</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 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data anonymisation is often required to comply with regulations when transfering information across departments or entities. However, the risk is that this procedure can distort the data and jeopardise the models built on it. Intuitively, the process of training an NLP model on anonymised data may lower the performance of the resulting model when compared to a model trained on non-anonymised data. In this paper, we investigate the impact of de-identification on the performance of nine downstream NLP tasks. We focus on the anonymisation and pseudonymisation of personal names and compare six different anonymisation strategies for two state-of-the-art pre-trained models. Based on these experiments, we formulate recommendations on how the de-identification should be performed to guarantee accurate NLP models. Our results reveal that de-identification does have a negative impact on the performance of NLP models, but this impact is relatively low. We also find that using pseudonymisation techniques involving random names leads to better performance across most tasks.</abstract>
<identifier type="citekey">lothritz-etal-2023-evaluating</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.2</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>10</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Impact of Text De-Identification on Downstream NLP Tasks
%A Lothritz, Cedric
%A Lebichot, Bertrand
%A Allix, Kevin
%A Ezzini, Saad
%A Bissyandé, Tegawendé
%A Klein, Jacques
%A Boytsov, Andrey
%A Lefebvre, Clément
%A Goujon, Anne
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F lothritz-etal-2023-evaluating
%X Data anonymisation is often required to comply with regulations when transfering information across departments or entities. However, the risk is that this procedure can distort the data and jeopardise the models built on it. Intuitively, the process of training an NLP model on anonymised data may lower the performance of the resulting model when compared to a model trained on non-anonymised data. In this paper, we investigate the impact of de-identification on the performance of nine downstream NLP tasks. We focus on the anonymisation and pseudonymisation of personal names and compare six different anonymisation strategies for two state-of-the-art pre-trained models. Based on these experiments, we formulate recommendations on how the de-identification should be performed to guarantee accurate NLP models. Our results reveal that de-identification does have a negative impact on the performance of NLP models, but this impact is relatively low. We also find that using pseudonymisation techniques involving random names leads to better performance across most tasks.
%U https://aclanthology.org/2023.nodalida-1.2
%P 10-16
Markdown (Informal)
[Evaluating the Impact of Text De-Identification on Downstream NLP Tasks](https://aclanthology.org/2023.nodalida-1.2) (Lothritz et al., NoDaLiDa 2023)
ACL
- Cedric Lothritz, Bertrand Lebichot, Kevin Allix, Saad Ezzini, Tegawendé Bissyandé, Jacques Klein, Andrey Boytsov, Clément Lefebvre, and Anne Goujon. 2023. Evaluating the Impact of Text De-Identification on Downstream NLP Tasks. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 10–16, Tórshavn, Faroe Islands. University of Tartu Library.