@inproceedings{emelyanov-2021-towards,
title = "Towards Task-Agnostic Privacy- and Utility-Preserving Models",
author = "Emelyanov, Yaroslav",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.45",
pages = "394--401",
abstract = "Modern deep learning models for natural language processing rely heavily on large amounts of annotated texts. However, obtaining such texts may be difficult when they contain personal or confidential information, for example, in health or legal domains. In this work, we propose a method of de-identifying free-form text documents by carefully redacting sensitive data in them. We show that our method preserves data utility for text classification, sequence labeling and question answering tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="emelyanov-2021-towards">
<titleInfo>
<title>Towards Task-Agnostic Privacy- and Utility-Preserving Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaroslav</namePart>
<namePart type="family">Emelyanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Modern deep learning models for natural language processing rely heavily on large amounts of annotated texts. However, obtaining such texts may be difficult when they contain personal or confidential information, for example, in health or legal domains. In this work, we propose a method of de-identifying free-form text documents by carefully redacting sensitive data in them. We show that our method preserves data utility for text classification, sequence labeling and question answering tasks.</abstract>
<identifier type="citekey">emelyanov-2021-towards</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.45</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>394</start>
<end>401</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Task-Agnostic Privacy- and Utility-Preserving Models
%A Emelyanov, Yaroslav
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F emelyanov-2021-towards
%X Modern deep learning models for natural language processing rely heavily on large amounts of annotated texts. However, obtaining such texts may be difficult when they contain personal or confidential information, for example, in health or legal domains. In this work, we propose a method of de-identifying free-form text documents by carefully redacting sensitive data in them. We show that our method preserves data utility for text classification, sequence labeling and question answering tasks.
%U https://aclanthology.org/2021.ranlp-1.45
%P 394-401
Markdown (Informal)
[Towards Task-Agnostic Privacy- and Utility-Preserving Models](https://aclanthology.org/2021.ranlp-1.45) (Emelyanov, RANLP 2021)
ACL