@inproceedings{chambers-etal-2019-character,
title = "Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking",
author = "Chambers, Nathanael and
Forman, Timothy and
Griswold, Catherine and
Lu, Kevin and
Khastgir, Yogaish and
Steckler, Stephen",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5507",
doi = "10.18653/v1/D19-5507",
pages = "48--56",
abstract = "Illicit activity on the Web often uses noisy text to obscure information between client and seller, such as the seller{'}s phone number. This presents an interesting challenge to language understanding systems; how do we model adversarial noise in a text extraction system? This paper addresses the sex trafficking domain, and proposes some of the first neural network architectures to learn and extract phone numbers from noisy text. We create a new adversarial advertisement dataset, propose several RNN-based models to solve the problem, and most notably propose a visual character language model to interpret unseen unicode characters. We train a CRF jointly with a CNN to improve number recognition by 89{\%} over just a CRF. Through data augmentation in this unique model, we present the first results on characters never seen in training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chambers-etal-2019-character">
<titleInfo>
<title>Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathanael</namePart>
<namePart type="family">Chambers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Forman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Griswold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yogaish</namePart>
<namePart type="family">Khastgir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Steckler</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 5th Workshop on Noisy User-generated Text (W-NUT 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>Illicit activity on the Web often uses noisy text to obscure information between client and seller, such as the seller’s phone number. This presents an interesting challenge to language understanding systems; how do we model adversarial noise in a text extraction system? This paper addresses the sex trafficking domain, and proposes some of the first neural network architectures to learn and extract phone numbers from noisy text. We create a new adversarial advertisement dataset, propose several RNN-based models to solve the problem, and most notably propose a visual character language model to interpret unseen unicode characters. We train a CRF jointly with a CNN to improve number recognition by 89% over just a CRF. Through data augmentation in this unique model, we present the first results on characters never seen in training.</abstract>
<identifier type="citekey">chambers-etal-2019-character</identifier>
<identifier type="doi">10.18653/v1/D19-5507</identifier>
<location>
<url>https://aclanthology.org/D19-5507</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>48</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking
%A Chambers, Nathanael
%A Forman, Timothy
%A Griswold, Catherine
%A Lu, Kevin
%A Khastgir, Yogaish
%A Steckler, Stephen
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F chambers-etal-2019-character
%X Illicit activity on the Web often uses noisy text to obscure information between client and seller, such as the seller’s phone number. This presents an interesting challenge to language understanding systems; how do we model adversarial noise in a text extraction system? This paper addresses the sex trafficking domain, and proposes some of the first neural network architectures to learn and extract phone numbers from noisy text. We create a new adversarial advertisement dataset, propose several RNN-based models to solve the problem, and most notably propose a visual character language model to interpret unseen unicode characters. We train a CRF jointly with a CNN to improve number recognition by 89% over just a CRF. Through data augmentation in this unique model, we present the first results on characters never seen in training.
%R 10.18653/v1/D19-5507
%U https://aclanthology.org/D19-5507
%U https://doi.org/10.18653/v1/D19-5507
%P 48-56
Markdown (Informal)
[Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking](https://aclanthology.org/D19-5507) (Chambers et al., WNUT 2019)
ACL