@inproceedings{lu-etal-2020-diverging,
title = "Diverging Divergences: Examining Variants of {J}ensen {S}hannon Divergence for Corpus Comparison Tasks",
author = "Lu, Jinghui and
Henchion, Maeve and
Mac Namee, Brian",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.832",
pages = "6740--6744",
abstract = "Jensen-Shannon divergence (JSD) is a distribution similarity measurement widely used in natural language processing. In corpus comparison tasks, where keywords are extracted to reveal the divergence between different corpora (for example, social media posts from proponents of different views on a political issue), two variants of JSD have emerged in the literature. One of these uses a weighting based on the relative sizes of the corpora being compared. In this paper we argue that this weighting is unnecessary and, in fact, can lead to misleading results. We recommend that this weighted version is not used. We base this recommendation on an analysis of the JSD variants and experiments showing how they impact corpus comparison results as the relative sizes of the corpora being compared change.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2020-diverging">
<titleInfo>
<title>Diverging Divergences: Examining Variants of Jensen Shannon Divergence for Corpus Comparison Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinghui</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maeve</namePart>
<namePart type="family">Henchion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Mac Namee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Jensen-Shannon divergence (JSD) is a distribution similarity measurement widely used in natural language processing. In corpus comparison tasks, where keywords are extracted to reveal the divergence between different corpora (for example, social media posts from proponents of different views on a political issue), two variants of JSD have emerged in the literature. One of these uses a weighting based on the relative sizes of the corpora being compared. In this paper we argue that this weighting is unnecessary and, in fact, can lead to misleading results. We recommend that this weighted version is not used. We base this recommendation on an analysis of the JSD variants and experiments showing how they impact corpus comparison results as the relative sizes of the corpora being compared change.</abstract>
<identifier type="citekey">lu-etal-2020-diverging</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.832</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6740</start>
<end>6744</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diverging Divergences: Examining Variants of Jensen Shannon Divergence for Corpus Comparison Tasks
%A Lu, Jinghui
%A Henchion, Maeve
%A Mac Namee, Brian
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F lu-etal-2020-diverging
%X Jensen-Shannon divergence (JSD) is a distribution similarity measurement widely used in natural language processing. In corpus comparison tasks, where keywords are extracted to reveal the divergence between different corpora (for example, social media posts from proponents of different views on a political issue), two variants of JSD have emerged in the literature. One of these uses a weighting based on the relative sizes of the corpora being compared. In this paper we argue that this weighting is unnecessary and, in fact, can lead to misleading results. We recommend that this weighted version is not used. We base this recommendation on an analysis of the JSD variants and experiments showing how they impact corpus comparison results as the relative sizes of the corpora being compared change.
%U https://aclanthology.org/2020.lrec-1.832
%P 6740-6744
Markdown (Informal)
[Diverging Divergences: Examining Variants of Jensen Shannon Divergence for Corpus Comparison Tasks](https://aclanthology.org/2020.lrec-1.832) (Lu et al., LREC 2020)
ACL