Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking

Nathanael Chambers, Timothy Forman, Catherine Griswold, Kevin Lu, Yogaish Khastgir, Stephen Steckler


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.
Anthology ID:
D19-5507
Volume:
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
48–56
Language:
URL:
https://aclanthology.org/D19-5507
DOI:
10.18653/v1/D19-5507
Bibkey:
Cite (ACL):
Nathanael Chambers, Timothy Forman, Catherine Griswold, Kevin Lu, Yogaish Khastgir, and Stephen Steckler. 2019. Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pages 48–56, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking (Chambers et al., WNUT 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5507.pdf