@inproceedings{xu-etal-2020-personal,
title = "Personal Information Leakage Detection in Conversations",
author = "Xu, Qiongkai and
Qu, Lizhen and
Gao, Zeyu and
Haffari, Gholamreza",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.532",
doi = "10.18653/v1/2020.emnlp-main.532",
pages = "6567--6580",
abstract = "The global market size of conversational assistants (chatbots) is expected to grow to USD 9.4 billion by 2024, according to MarketsandMarkets. Despite the wide use of chatbots, leakage of personal information through chatbots poses serious privacy concerns for their users. In this work, we propose to protect personal information by warning users of detected suspicious sentences generated by conversational assistants. The detection task is formulated as an alignment optimization problem and a new dataset PERSONA-LEAKAGE is collected for evaluation. In this paper, we propose two novel constrained alignment models, which consistently outperform baseline methods on Moreover, we conduct analysis on the behavior of recently proposed personalized chit-chat dialogue systems. The empirical results show that those systems suffer more from personal information disclosure than the widely used Seq2Seq model and the language model. In those cases, a significant number of information leaking utterances can be detected by our models with high precision.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2020-personal">
<titleInfo>
<title>Personal Information Leakage Detection in Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiongkai</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhen</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyu</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The global market size of conversational assistants (chatbots) is expected to grow to USD 9.4 billion by 2024, according to MarketsandMarkets. Despite the wide use of chatbots, leakage of personal information through chatbots poses serious privacy concerns for their users. In this work, we propose to protect personal information by warning users of detected suspicious sentences generated by conversational assistants. The detection task is formulated as an alignment optimization problem and a new dataset PERSONA-LEAKAGE is collected for evaluation. In this paper, we propose two novel constrained alignment models, which consistently outperform baseline methods on Moreover, we conduct analysis on the behavior of recently proposed personalized chit-chat dialogue systems. The empirical results show that those systems suffer more from personal information disclosure than the widely used Seq2Seq model and the language model. In those cases, a significant number of information leaking utterances can be detected by our models with high precision.</abstract>
<identifier type="citekey">xu-etal-2020-personal</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.532</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.532</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>6567</start>
<end>6580</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personal Information Leakage Detection in Conversations
%A Xu, Qiongkai
%A Qu, Lizhen
%A Gao, Zeyu
%A Haffari, Gholamreza
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F xu-etal-2020-personal
%X The global market size of conversational assistants (chatbots) is expected to grow to USD 9.4 billion by 2024, according to MarketsandMarkets. Despite the wide use of chatbots, leakage of personal information through chatbots poses serious privacy concerns for their users. In this work, we propose to protect personal information by warning users of detected suspicious sentences generated by conversational assistants. The detection task is formulated as an alignment optimization problem and a new dataset PERSONA-LEAKAGE is collected for evaluation. In this paper, we propose two novel constrained alignment models, which consistently outperform baseline methods on Moreover, we conduct analysis on the behavior of recently proposed personalized chit-chat dialogue systems. The empirical results show that those systems suffer more from personal information disclosure than the widely used Seq2Seq model and the language model. In those cases, a significant number of information leaking utterances can be detected by our models with high precision.
%R 10.18653/v1/2020.emnlp-main.532
%U https://aclanthology.org/2020.emnlp-main.532
%U https://doi.org/10.18653/v1/2020.emnlp-main.532
%P 6567-6580
Markdown (Informal)
[Personal Information Leakage Detection in Conversations](https://aclanthology.org/2020.emnlp-main.532) (Xu et al., EMNLP 2020)
ACL
- Qiongkai Xu, Lizhen Qu, Zeyu Gao, and Gholamreza Haffari. 2020. Personal Information Leakage Detection in Conversations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6567–6580, Online. Association for Computational Linguistics.