@inproceedings{m-benatti-etal-2022-disclose,
title = "Should {I} disclose my dataset? Caveats between reproducibility and individual data rights",
author = "Benatti, Raysa M. and
Villarroel, Camila M. L. and
Avila, Sandra and
Colombini, Esther L. and
Severi, Fabiana",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nllp-1.20",
doi = "10.18653/v1/2022.nllp-1.20",
pages = "228--237",
abstract = "Natural language processing techniques have helped domain experts solve legal problems. Digital availability of court documents increases possibilities for researchers, who can access them as a source for building datasets {---} whose disclosure is aligned with good reproducibility practices in computational research. Large and digitized court systems, such as the Brazilian one, are prone to be explored in that sense. However, personal data protection laws impose restrictions on data exposure and state principles about which researchers should be mindful. Special caution must be taken in cases with human rights violations, such as gender discrimination, over which we elaborate as an example of interest. We present legal and ethical considerations on the issue, as well as guidelines for researchers dealing with this kind of data and deciding whether to disclose it.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="m-benatti-etal-2022-disclose">
<titleInfo>
<title>Should I disclose my dataset? Caveats between reproducibility and individual data rights</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raysa</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Benatti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camila</namePart>
<namePart type="given">M</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Villarroel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Avila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esther</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Colombini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabiana</namePart>
<namePart type="family">Severi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language processing techniques have helped domain experts solve legal problems. Digital availability of court documents increases possibilities for researchers, who can access them as a source for building datasets — whose disclosure is aligned with good reproducibility practices in computational research. Large and digitized court systems, such as the Brazilian one, are prone to be explored in that sense. However, personal data protection laws impose restrictions on data exposure and state principles about which researchers should be mindful. Special caution must be taken in cases with human rights violations, such as gender discrimination, over which we elaborate as an example of interest. We present legal and ethical considerations on the issue, as well as guidelines for researchers dealing with this kind of data and deciding whether to disclose it.</abstract>
<identifier type="citekey">m-benatti-etal-2022-disclose</identifier>
<identifier type="doi">10.18653/v1/2022.nllp-1.20</identifier>
<location>
<url>https://aclanthology.org/2022.nllp-1.20</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>228</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Should I disclose my dataset? Caveats between reproducibility and individual data rights
%A Benatti, Raysa M.
%A Villarroel, Camila M. L.
%A Avila, Sandra
%A Colombini, Esther L.
%A Severi, Fabiana
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%S Proceedings of the Natural Legal Language Processing Workshop 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F m-benatti-etal-2022-disclose
%X Natural language processing techniques have helped domain experts solve legal problems. Digital availability of court documents increases possibilities for researchers, who can access them as a source for building datasets — whose disclosure is aligned with good reproducibility practices in computational research. Large and digitized court systems, such as the Brazilian one, are prone to be explored in that sense. However, personal data protection laws impose restrictions on data exposure and state principles about which researchers should be mindful. Special caution must be taken in cases with human rights violations, such as gender discrimination, over which we elaborate as an example of interest. We present legal and ethical considerations on the issue, as well as guidelines for researchers dealing with this kind of data and deciding whether to disclose it.
%R 10.18653/v1/2022.nllp-1.20
%U https://aclanthology.org/2022.nllp-1.20
%U https://doi.org/10.18653/v1/2022.nllp-1.20
%P 228-237
Markdown (Informal)
[Should I disclose my dataset? Caveats between reproducibility and individual data rights](https://aclanthology.org/2022.nllp-1.20) (Benatti et al., NLLP 2022)
ACL