@inproceedings{jabbari-etal-2008-using,
title = "Using a Probabilistic Model of Context to Detect Word Obfuscation",
author = "Jabbari, Sanaz and
Allison, Ben and
Guthrie, Louise",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/560_paper.pdf",
abstract = "This paper proposes a distributional model of word use and word meaning which is derived purely from a body of text, and then applies this model to determine whether certain words are used in or out of context. We suggest that we can view the contexts of words as multinomially distributed random variables. We illustrate how using this basic idea, we can formulate the problem of detecting whether or not a word is used in context as a likelihood ratio test. We also define a measure of semantic relatedness between a word and its context using the same model. We assume that words that typically appear together are related, and thus have similar probability distributions and that words used in an unusual way will have probability distributions which are dissimilar from those of their surrounding context. The relatedness of a word to its context is based on Kullback-Leibler divergence between probability distributions assigned to the constituent words in the given sentence. We employed our methods on a defense-oriented application where certain words are substituted with other words in an intercepted communication.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jabbari-etal-2008-using">
<titleInfo>
<title>Using a Probabilistic Model of Context to Detect Word Obfuscation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanaz</namePart>
<namePart type="family">Jabbari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Allison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louise</namePart>
<namePart type="family">Guthrie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes a distributional model of word use and word meaning which is derived purely from a body of text, and then applies this model to determine whether certain words are used in or out of context. We suggest that we can view the contexts of words as multinomially distributed random variables. We illustrate how using this basic idea, we can formulate the problem of detecting whether or not a word is used in context as a likelihood ratio test. We also define a measure of semantic relatedness between a word and its context using the same model. We assume that words that typically appear together are related, and thus have similar probability distributions and that words used in an unusual way will have probability distributions which are dissimilar from those of their surrounding context. The relatedness of a word to its context is based on Kullback-Leibler divergence between probability distributions assigned to the constituent words in the given sentence. We employed our methods on a defense-oriented application where certain words are substituted with other words in an intercepted communication.</abstract>
<identifier type="citekey">jabbari-etal-2008-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/560_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using a Probabilistic Model of Context to Detect Word Obfuscation
%A Jabbari, Sanaz
%A Allison, Ben
%A Guthrie, Louise
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F jabbari-etal-2008-using
%X This paper proposes a distributional model of word use and word meaning which is derived purely from a body of text, and then applies this model to determine whether certain words are used in or out of context. We suggest that we can view the contexts of words as multinomially distributed random variables. We illustrate how using this basic idea, we can formulate the problem of detecting whether or not a word is used in context as a likelihood ratio test. We also define a measure of semantic relatedness between a word and its context using the same model. We assume that words that typically appear together are related, and thus have similar probability distributions and that words used in an unusual way will have probability distributions which are dissimilar from those of their surrounding context. The relatedness of a word to its context is based on Kullback-Leibler divergence between probability distributions assigned to the constituent words in the given sentence. We employed our methods on a defense-oriented application where certain words are substituted with other words in an intercepted communication.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/560_paper.pdf
Markdown (Informal)
[Using a Probabilistic Model of Context to Detect Word Obfuscation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/560_paper.pdf) (Jabbari et al., LREC 2008)
ACL