@inproceedings{meehan-etal-2022-sentence,
title = "Sentence-level Privacy for Document Embeddings",
author = "Meehan, Casey and
Mrini, Khalil and
Chaudhuri, Kamalika",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.238",
doi = "10.18653/v1/2022.acl-long.238",
pages = "3367--3380",
abstract = "User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their data. In this work we propose SentDP, pure local differential privacy at the sentence level for a single user document. We propose a novel technique, DeepCandidate, that combines concepts from robust statistics and language modeling to produce high (768) dimensional, general $\epsilon$-SentDP document embeddings. This guarantees that any single sentence in a document can be substituted with any other sentence while keeping the embedding $\epsilon$-indistinguishable. Our experiments indicate that these private document embeddings are useful for downstream tasks like sentiment analysis and topic classification and even outperform baseline methods with weaker guarantees like word-level Metric DP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meehan-etal-2022-sentence">
<titleInfo>
<title>Sentence-level Privacy for Document Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Meehan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kamalika</namePart>
<namePart type="family">Chaudhuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their data. In this work we propose SentDP, pure local differential privacy at the sentence level for a single user document. We propose a novel technique, DeepCandidate, that combines concepts from robust statistics and language modeling to produce high (768) dimensional, general ε-SentDP document embeddings. This guarantees that any single sentence in a document can be substituted with any other sentence while keeping the embedding ε-indistinguishable. Our experiments indicate that these private document embeddings are useful for downstream tasks like sentiment analysis and topic classification and even outperform baseline methods with weaker guarantees like word-level Metric DP.</abstract>
<identifier type="citekey">meehan-etal-2022-sentence</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.238</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.238</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>3367</start>
<end>3380</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence-level Privacy for Document Embeddings
%A Meehan, Casey
%A Mrini, Khalil
%A Chaudhuri, Kamalika
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F meehan-etal-2022-sentence
%X User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their data. In this work we propose SentDP, pure local differential privacy at the sentence level for a single user document. We propose a novel technique, DeepCandidate, that combines concepts from robust statistics and language modeling to produce high (768) dimensional, general ε-SentDP document embeddings. This guarantees that any single sentence in a document can be substituted with any other sentence while keeping the embedding ε-indistinguishable. Our experiments indicate that these private document embeddings are useful for downstream tasks like sentiment analysis and topic classification and even outperform baseline methods with weaker guarantees like word-level Metric DP.
%R 10.18653/v1/2022.acl-long.238
%U https://aclanthology.org/2022.acl-long.238
%U https://doi.org/10.18653/v1/2022.acl-long.238
%P 3367-3380
Markdown (Informal)
[Sentence-level Privacy for Document Embeddings](https://aclanthology.org/2022.acl-long.238) (Meehan et al., ACL 2022)
ACL
- Casey Meehan, Khalil Mrini, and Kamalika Chaudhuri. 2022. Sentence-level Privacy for Document Embeddings. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3367–3380, Dublin, Ireland. Association for Computational Linguistics.