@inproceedings{cabrera-diego-gheewala-2024-psilence,
title = "{PSILENCE}: A Pseudonymization Tool for International Law",
author = "Cabrera-Diego, Luis Adri{\'a}n and
Gheewala, Akshita",
editor = {Volodina, Elena and
Alfter, David and
Dobnik, Simon and
Lindstr{\"o}m Tiedemann, Therese and
Mu{\~n}oz S{\'a}nchez, Ricardo and
Szawerna, Maria Irena and
Vu, Xuan-Son},
booktitle = "Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.caldpseudo-1.4/",
pages = "25--36",
abstract = "Since the announcement of the GDPR, the pseudonymization of legal documents has become a high-priority task in many legal organizations. This means that for making public a document, it is necessary to redact the identity of certain entities, such as witnesses. In this work, we present the first results obtained by PSILENCE, a pseudonymization tool created for redacting semi-automatically international arbitration documents in English. PSILENCE has been built using a Named Entity Recognition (NER) system, along with a Coreference Resolution system. These systems allow us to find the people that we need to redact in a clustered way, but also to propose the same pseudonym throughout one document. This last aspect makes it easier to read and comprehend a redacted legal document. Different experiments were done on four different datasets, one of which was legal, and the results are promising, reaching a Macro F-score of up to 0.72 on the legal dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cabrera-diego-gheewala-2024-psilence">
<titleInfo>
<title>PSILENCE: A Pseudonymization Tool for International Law</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Adrián</namePart>
<namePart type="family">Cabrera-Diego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshita</namePart>
<namePart type="family">Gheewala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Lindström Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Since the announcement of the GDPR, the pseudonymization of legal documents has become a high-priority task in many legal organizations. This means that for making public a document, it is necessary to redact the identity of certain entities, such as witnesses. In this work, we present the first results obtained by PSILENCE, a pseudonymization tool created for redacting semi-automatically international arbitration documents in English. PSILENCE has been built using a Named Entity Recognition (NER) system, along with a Coreference Resolution system. These systems allow us to find the people that we need to redact in a clustered way, but also to propose the same pseudonym throughout one document. This last aspect makes it easier to read and comprehend a redacted legal document. Different experiments were done on four different datasets, one of which was legal, and the results are promising, reaching a Macro F-score of up to 0.72 on the legal dataset.</abstract>
<identifier type="citekey">cabrera-diego-gheewala-2024-psilence</identifier>
<location>
<url>https://aclanthology.org/2024.caldpseudo-1.4/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>25</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PSILENCE: A Pseudonymization Tool for International Law
%A Cabrera-Diego, Luis Adrián
%A Gheewala, Akshita
%Y Volodina, Elena
%Y Alfter, David
%Y Dobnik, Simon
%Y Lindström Tiedemann, Therese
%Y Muñoz Sánchez, Ricardo
%Y Szawerna, Maria Irena
%Y Vu, Xuan-Son
%S Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F cabrera-diego-gheewala-2024-psilence
%X Since the announcement of the GDPR, the pseudonymization of legal documents has become a high-priority task in many legal organizations. This means that for making public a document, it is necessary to redact the identity of certain entities, such as witnesses. In this work, we present the first results obtained by PSILENCE, a pseudonymization tool created for redacting semi-automatically international arbitration documents in English. PSILENCE has been built using a Named Entity Recognition (NER) system, along with a Coreference Resolution system. These systems allow us to find the people that we need to redact in a clustered way, but also to propose the same pseudonym throughout one document. This last aspect makes it easier to read and comprehend a redacted legal document. Different experiments were done on four different datasets, one of which was legal, and the results are promising, reaching a Macro F-score of up to 0.72 on the legal dataset.
%U https://aclanthology.org/2024.caldpseudo-1.4/
%P 25-36
Markdown (Informal)
[PSILENCE: A Pseudonymization Tool for International Law](https://aclanthology.org/2024.caldpseudo-1.4/) (Cabrera-Diego & Gheewala, CALD-pseudo 2024)
ACL
- Luis Adrián Cabrera-Diego and Akshita Gheewala. 2024. PSILENCE: A Pseudonymization Tool for International Law. In Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024), pages 25–36, St. Julian’s, Malta. Association for Computational Linguistics.