<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="plant-etal-2021-cape">
    <titleInfo>
        <title>CAPE: Context-Aware Private Embeddings for Private Language Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Richard</namePart>
        <namePart type="family">Plant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dimitra</namePart>
        <namePart type="family">Gkatzia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Valerio</namePart>
        <namePart type="family">Giuffrida</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural language models have contributed to state-of-the-art results in a number of downstream applications including sentiment analysis, intent classification and others. However, obtaining text representations or embeddings using these models risks encoding personally identifiable information learned from language and context cues that may lead to privacy leaks. To ameliorate this issue, we propose Context-Aware Private Embeddings (CAPE), a novel approach which combines differential privacy and adversarial learning to preserve privacy during training of embeddings. Specifically, CAPE firstly applies calibrated noise through differential privacy to maintain the privacy of text representations by preserving the encoded semantic links while obscuring sensitive information. Next, CAPE employs an adversarial training regime that obscures identified private variables. Experimental results demonstrate that our proposed approach is more effective in reducing private information leakage than either single intervention, with approximately a 3% reduction in attacker performance compared to the best-performing current method.</abstract>
    <identifier type="citekey">plant-etal-2021-cape</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.628</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.628</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>7970</start>
            <end>7978</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CAPE: Context-Aware Private Embeddings for Private Language Learning
%A Plant, Richard
%A Gkatzia, Dimitra
%A Giuffrida, Valerio
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F plant-etal-2021-cape
%X Neural language models have contributed to state-of-the-art results in a number of downstream applications including sentiment analysis, intent classification and others. However, obtaining text representations or embeddings using these models risks encoding personally identifiable information learned from language and context cues that may lead to privacy leaks. To ameliorate this issue, we propose Context-Aware Private Embeddings (CAPE), a novel approach which combines differential privacy and adversarial learning to preserve privacy during training of embeddings. Specifically, CAPE firstly applies calibrated noise through differential privacy to maintain the privacy of text representations by preserving the encoded semantic links while obscuring sensitive information. Next, CAPE employs an adversarial training regime that obscures identified private variables. Experimental results demonstrate that our proposed approach is more effective in reducing private information leakage than either single intervention, with approximately a 3% reduction in attacker performance compared to the best-performing current method.
%R 10.18653/v1/2021.emnlp-main.628
%U https://aclanthology.org/2021.emnlp-main.628
%U https://doi.org/10.18653/v1/2021.emnlp-main.628
%P 7970-7978

Markdown (Informal)

[CAPE: Context-Aware Private Embeddings for Private Language Learning](https://aclanthology.org/2021.emnlp-main.628) (Plant et al., EMNLP 2021)

• CAPE: Context-Aware Private Embeddings for Private Language Learning (Plant et al., EMNLP 2021)

ACL

• Richard Plant, Dimitra Gkatzia, and Valerio Giuffrida. 2021. CAPE: Context-Aware Private Embeddings for Private Language Learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7970–7978, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.