@inproceedings{papadopoulou-etal-2022-bootstrapping,
title = "Bootstrapping Text Anonymization Models with Distant Supervision",
author = "Papadopoulou, Anthi and
Lison, Pierre and
{\O}vrelid, Lilja and
Pil{\'a}n, Ildik{\'o}",
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-1.476",
pages = "4477--4487",
abstract = "We propose a novel method to bootstrap text anonymization models based on distant supervision. Instead of requiring manually labeled training data, the approach relies on a knowledge graph expressing the background information assumed to be publicly available about various individuals. This knowledge graph is employed to automatically annotate text documents including personal data about a subset of those individuals. More precisely, the method determines which text spans ought to be masked in order to guarantee k-anonymity, assuming an adversary with access to both the text documents and the background information expressed in the knowledge graph. The resulting collection of labeled documents is then used as training data to fine-tune a pre-trained language model for text anonymization. We illustrate this approach using a knowledge graph extracted from Wikidata and short biographical texts from Wikipedia. Evaluation results with a RoBERTa-based model and a manually annotated collection of 553 summaries showcase the potential of the approach, but also unveil a number of issues that may arise if the knowledge graph is noisy or incomplete. The results also illustrate that, contrary to most sequence labeling problems, the text anonymization task may admit several alternative solutions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papadopoulou-etal-2022-bootstrapping">
<titleInfo>
<title>Bootstrapping Text Anonymization Models with Distant Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anthi</namePart>
<namePart type="family">Papadopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Lison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</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>We propose a novel method to bootstrap text anonymization models based on distant supervision. Instead of requiring manually labeled training data, the approach relies on a knowledge graph expressing the background information assumed to be publicly available about various individuals. This knowledge graph is employed to automatically annotate text documents including personal data about a subset of those individuals. More precisely, the method determines which text spans ought to be masked in order to guarantee k-anonymity, assuming an adversary with access to both the text documents and the background information expressed in the knowledge graph. The resulting collection of labeled documents is then used as training data to fine-tune a pre-trained language model for text anonymization. We illustrate this approach using a knowledge graph extracted from Wikidata and short biographical texts from Wikipedia. Evaluation results with a RoBERTa-based model and a manually annotated collection of 553 summaries showcase the potential of the approach, but also unveil a number of issues that may arise if the knowledge graph is noisy or incomplete. The results also illustrate that, contrary to most sequence labeling problems, the text anonymization task may admit several alternative solutions.</abstract>
<identifier type="citekey">papadopoulou-etal-2022-bootstrapping</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.476</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4477</start>
<end>4487</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bootstrapping Text Anonymization Models with Distant Supervision
%A Papadopoulou, Anthi
%A Lison, Pierre
%A Øvrelid, Lilja
%A Pilán, Ildikó
%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 papadopoulou-etal-2022-bootstrapping
%X We propose a novel method to bootstrap text anonymization models based on distant supervision. Instead of requiring manually labeled training data, the approach relies on a knowledge graph expressing the background information assumed to be publicly available about various individuals. This knowledge graph is employed to automatically annotate text documents including personal data about a subset of those individuals. More precisely, the method determines which text spans ought to be masked in order to guarantee k-anonymity, assuming an adversary with access to both the text documents and the background information expressed in the knowledge graph. The resulting collection of labeled documents is then used as training data to fine-tune a pre-trained language model for text anonymization. We illustrate this approach using a knowledge graph extracted from Wikidata and short biographical texts from Wikipedia. Evaluation results with a RoBERTa-based model and a manually annotated collection of 553 summaries showcase the potential of the approach, but also unveil a number of issues that may arise if the knowledge graph is noisy or incomplete. The results also illustrate that, contrary to most sequence labeling problems, the text anonymization task may admit several alternative solutions.
%U https://aclanthology.org/2022.lrec-1.476
%P 4477-4487
Markdown (Informal)
[Bootstrapping Text Anonymization Models with Distant Supervision](https://aclanthology.org/2022.lrec-1.476) (Papadopoulou et al., LREC 2022)
ACL