@inproceedings{melamud-goldberger-2017-information,
title = "Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function",
author = "Melamud, Oren and
Goldberger, Jacob",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-2026",
doi = "10.18653/v1/P17-2026",
pages = "167--171",
abstract = "In this paper we define a measure of dependency between two random variables, based on the Jensen-Shannon (JS) divergence between their joint distribution and the product of their marginal distributions. Then, we show that word2vec{'}s skip-gram with negative sampling embedding algorithm finds the optimal low-dimensional approximation of this JS dependency measure between the words and their contexts. The gap between the optimal score and the low-dimensional approximation is demonstrated on a standard text corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="melamud-goldberger-2017-information">
<titleInfo>
<title>Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="family">Melamud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Goldberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we define a measure of dependency between two random variables, based on the Jensen-Shannon (JS) divergence between their joint distribution and the product of their marginal distributions. Then, we show that word2vec’s skip-gram with negative sampling embedding algorithm finds the optimal low-dimensional approximation of this JS dependency measure between the words and their contexts. The gap between the optimal score and the low-dimensional approximation is demonstrated on a standard text corpus.</abstract>
<identifier type="citekey">melamud-goldberger-2017-information</identifier>
<identifier type="doi">10.18653/v1/P17-2026</identifier>
<location>
<url>https://aclanthology.org/P17-2026</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>167</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function
%A Melamud, Oren
%A Goldberger, Jacob
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F melamud-goldberger-2017-information
%X In this paper we define a measure of dependency between two random variables, based on the Jensen-Shannon (JS) divergence between their joint distribution and the product of their marginal distributions. Then, we show that word2vec’s skip-gram with negative sampling embedding algorithm finds the optimal low-dimensional approximation of this JS dependency measure between the words and their contexts. The gap between the optimal score and the low-dimensional approximation is demonstrated on a standard text corpus.
%R 10.18653/v1/P17-2026
%U https://aclanthology.org/P17-2026
%U https://doi.org/10.18653/v1/P17-2026
%P 167-171
Markdown (Informal)
[Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function](https://aclanthology.org/P17-2026) (Melamud & Goldberger, ACL 2017)
ACL