@inproceedings{bevendorff-etal-2019-generalizing,
title = "Generalizing Unmasking for Short Texts",
author = "Bevendorff, Janek and
Stein, Benno and
Hagen, Matthias and
Potthast, Martin",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1068",
doi = "10.18653/v1/N19-1068",
pages = "654--659",
abstract = "Authorship verification is the problem of inferring whether two texts were written by the same author. For this task, unmasking is one of the most robust approaches as of today with the major shortcoming of only being applicable to book-length texts. In this paper, we present a generalized unmasking approach which allows for authorship verification of texts as short as four printed pages with very high precision at an adjustable recall tradeoff. Our generalized approach therefore reduces the required material by orders of magnitude, making unmasking applicable to authorship cases of more practical proportions. The new approach is on par with other state-of-the-art techniques that are optimized for texts of this length: it achieves accuracies of 75{--}80{\%}, while also allowing for easy adjustment to forensic scenarios that require higher levels of confidence in the classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bevendorff-etal-2019-generalizing">
<titleInfo>
<title>Generalizing Unmasking for Short Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janek</namePart>
<namePart type="family">Bevendorff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benno</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Hagen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Potthast</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Authorship verification is the problem of inferring whether two texts were written by the same author. For this task, unmasking is one of the most robust approaches as of today with the major shortcoming of only being applicable to book-length texts. In this paper, we present a generalized unmasking approach which allows for authorship verification of texts as short as four printed pages with very high precision at an adjustable recall tradeoff. Our generalized approach therefore reduces the required material by orders of magnitude, making unmasking applicable to authorship cases of more practical proportions. The new approach is on par with other state-of-the-art techniques that are optimized for texts of this length: it achieves accuracies of 75–80%, while also allowing for easy adjustment to forensic scenarios that require higher levels of confidence in the classification.</abstract>
<identifier type="citekey">bevendorff-etal-2019-generalizing</identifier>
<identifier type="doi">10.18653/v1/N19-1068</identifier>
<location>
<url>https://aclanthology.org/N19-1068</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>654</start>
<end>659</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalizing Unmasking for Short Texts
%A Bevendorff, Janek
%A Stein, Benno
%A Hagen, Matthias
%A Potthast, Martin
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F bevendorff-etal-2019-generalizing
%X Authorship verification is the problem of inferring whether two texts were written by the same author. For this task, unmasking is one of the most robust approaches as of today with the major shortcoming of only being applicable to book-length texts. In this paper, we present a generalized unmasking approach which allows for authorship verification of texts as short as four printed pages with very high precision at an adjustable recall tradeoff. Our generalized approach therefore reduces the required material by orders of magnitude, making unmasking applicable to authorship cases of more practical proportions. The new approach is on par with other state-of-the-art techniques that are optimized for texts of this length: it achieves accuracies of 75–80%, while also allowing for easy adjustment to forensic scenarios that require higher levels of confidence in the classification.
%R 10.18653/v1/N19-1068
%U https://aclanthology.org/N19-1068
%U https://doi.org/10.18653/v1/N19-1068
%P 654-659
Markdown (Informal)
[Generalizing Unmasking for Short Texts](https://aclanthology.org/N19-1068) (Bevendorff et al., NAACL 2019)
ACL
- Janek Bevendorff, Benno Stein, Matthias Hagen, and Martin Potthast. 2019. Generalizing Unmasking for Short Texts. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 654–659, Minneapolis, Minnesota. Association for Computational Linguistics.