@inproceedings{mosallanezhad-etal-2019-deep,
title = "Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference",
author = "Mosallanezhad, Ahmadreza and
Beigi, Ghazaleh and
Liu, Huan",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1240",
doi = "10.18653/v1/D19-1240",
pages = "2360--2369",
abstract = "User-generated textual data is rich in content and has been used in many user behavioral modeling tasks. However, it could also leak user private-attribute information that they may not want to disclose such as age and location. User{'}s privacy concerns mandate data publishers to protect privacy. One effective way is to anonymize the textual data. In this paper, we study the problem of textual data anonymization and propose a novel Reinforcement Learning-based Text Anonymizor, RLTA, which addresses the problem of private-attribute leakage while preserving the utility of textual data. Our approach first extracts a latent representation of the original text w.r.t. a given task, then leverages deep reinforcement learning to automatically learn an optimal strategy for manipulating text representations w.r.t. the received privacy and utility feedback. Experiments show the effectiveness of this approach in terms of preserving both privacy and utility.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mosallanezhad-etal-2019-deep">
<titleInfo>
<title>Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmadreza</namePart>
<namePart type="family">Mosallanezhad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ghazaleh</namePart>
<namePart type="family">Beigi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>User-generated textual data is rich in content and has been used in many user behavioral modeling tasks. However, it could also leak user private-attribute information that they may not want to disclose such as age and location. User’s privacy concerns mandate data publishers to protect privacy. One effective way is to anonymize the textual data. In this paper, we study the problem of textual data anonymization and propose a novel Reinforcement Learning-based Text Anonymizor, RLTA, which addresses the problem of private-attribute leakage while preserving the utility of textual data. Our approach first extracts a latent representation of the original text w.r.t. a given task, then leverages deep reinforcement learning to automatically learn an optimal strategy for manipulating text representations w.r.t. the received privacy and utility feedback. Experiments show the effectiveness of this approach in terms of preserving both privacy and utility.</abstract>
<identifier type="citekey">mosallanezhad-etal-2019-deep</identifier>
<identifier type="doi">10.18653/v1/D19-1240</identifier>
<location>
<url>https://aclanthology.org/D19-1240</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>2360</start>
<end>2369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference
%A Mosallanezhad, Ahmadreza
%A Beigi, Ghazaleh
%A Liu, Huan
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F mosallanezhad-etal-2019-deep
%X User-generated textual data is rich in content and has been used in many user behavioral modeling tasks. However, it could also leak user private-attribute information that they may not want to disclose such as age and location. User’s privacy concerns mandate data publishers to protect privacy. One effective way is to anonymize the textual data. In this paper, we study the problem of textual data anonymization and propose a novel Reinforcement Learning-based Text Anonymizor, RLTA, which addresses the problem of private-attribute leakage while preserving the utility of textual data. Our approach first extracts a latent representation of the original text w.r.t. a given task, then leverages deep reinforcement learning to automatically learn an optimal strategy for manipulating text representations w.r.t. the received privacy and utility feedback. Experiments show the effectiveness of this approach in terms of preserving both privacy and utility.
%R 10.18653/v1/D19-1240
%U https://aclanthology.org/D19-1240
%U https://doi.org/10.18653/v1/D19-1240
%P 2360-2369
Markdown (Informal)
[Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference](https://aclanthology.org/D19-1240) (Mosallanezhad et al., EMNLP-IJCNLP 2019)
ACL