@inproceedings{jiang-etal-2020-camouflaged,
title = "Camouflaged {C}hinese Spam Content Detection with Semi-supervised Generative Active Learning",
author = "Jiang, Zhuoren and
Gao, Zhe and
Duan, Yu and
Kang, Yangyang and
Sun, Changlong and
Zhang, Qiong and
Liu, Xiaozhong",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.279",
doi = "10.18653/v1/2020.acl-main.279",
pages = "3080--3085",
abstract = "We propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task. A {``}self-diversity{''} criterion is proposed for measuring the {``}worthiness{''} of a candidate for annotation. A semi-supervised variational autoencoder with masked attention learning approach and a character variation graph-enhanced augmentation procedure are proposed for data augmentation. The preliminary experiment demonstrates the proposed SIGNAL model is not only sensitive to spam sample selection, but also can improve the performance of a series of conventional active learning models for Chinese spam detection task. To the best of our knowledge, this is the first work to integrate active learning and semi-supervised generative learning for text spam detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2020-camouflaged">
<titleInfo>
<title>Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuoren</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangyang</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changlong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaozhong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</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>We propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task. A “self-diversity” criterion is proposed for measuring the “worthiness” of a candidate for annotation. A semi-supervised variational autoencoder with masked attention learning approach and a character variation graph-enhanced augmentation procedure are proposed for data augmentation. The preliminary experiment demonstrates the proposed SIGNAL model is not only sensitive to spam sample selection, but also can improve the performance of a series of conventional active learning models for Chinese spam detection task. To the best of our knowledge, this is the first work to integrate active learning and semi-supervised generative learning for text spam detection.</abstract>
<identifier type="citekey">jiang-etal-2020-camouflaged</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.279</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.279</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>3080</start>
<end>3085</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning
%A Jiang, Zhuoren
%A Gao, Zhe
%A Duan, Yu
%A Kang, Yangyang
%A Sun, Changlong
%A Zhang, Qiong
%A Liu, Xiaozhong
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F jiang-etal-2020-camouflaged
%X We propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task. A “self-diversity” criterion is proposed for measuring the “worthiness” of a candidate for annotation. A semi-supervised variational autoencoder with masked attention learning approach and a character variation graph-enhanced augmentation procedure are proposed for data augmentation. The preliminary experiment demonstrates the proposed SIGNAL model is not only sensitive to spam sample selection, but also can improve the performance of a series of conventional active learning models for Chinese spam detection task. To the best of our knowledge, this is the first work to integrate active learning and semi-supervised generative learning for text spam detection.
%R 10.18653/v1/2020.acl-main.279
%U https://aclanthology.org/2020.acl-main.279
%U https://doi.org/10.18653/v1/2020.acl-main.279
%P 3080-3085
Markdown (Informal)
[Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning](https://aclanthology.org/2020.acl-main.279) (Jiang et al., ACL 2020)
ACL