@inproceedings{fothergill-etal-2016-evaluating,
title = "Evaluating a Topic Modelling Approach to Measuring Corpus Similarity",
author = "Fothergill, Richard and
Cook, Paul and
Baldwin, Timothy",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1042",
pages = "273--279",
abstract = "Web corpora are often constructed automatically, and their contents are therefore often not well understood. One technique for assessing the composition of such a web corpus is to empirically measure its similarity to a reference corpus whose composition is known. In this paper we evaluate a number of measures of corpus similarity, including a method based on topic modelling which has not been previously evaluated for this task. To evaluate these methods we use known-similarity corpora that have been previously used for this purpose, as well as a number of newly-constructed known-similarity corpora targeting differences in genre, topic, time, and region. Our findings indicate that, overall, the topic modelling approach did not improve on a chi-square method that had previously been found to work well for measuring corpus similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fothergill-etal-2016-evaluating">
<titleInfo>
<title>Evaluating a Topic Modelling Approach to Measuring Corpus Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Fothergill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Web corpora are often constructed automatically, and their contents are therefore often not well understood. One technique for assessing the composition of such a web corpus is to empirically measure its similarity to a reference corpus whose composition is known. In this paper we evaluate a number of measures of corpus similarity, including a method based on topic modelling which has not been previously evaluated for this task. To evaluate these methods we use known-similarity corpora that have been previously used for this purpose, as well as a number of newly-constructed known-similarity corpora targeting differences in genre, topic, time, and region. Our findings indicate that, overall, the topic modelling approach did not improve on a chi-square method that had previously been found to work well for measuring corpus similarity.</abstract>
<identifier type="citekey">fothergill-etal-2016-evaluating</identifier>
<location>
<url>https://aclanthology.org/L16-1042</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>273</start>
<end>279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating a Topic Modelling Approach to Measuring Corpus Similarity
%A Fothergill, Richard
%A Cook, Paul
%A Baldwin, Timothy
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F fothergill-etal-2016-evaluating
%X Web corpora are often constructed automatically, and their contents are therefore often not well understood. One technique for assessing the composition of such a web corpus is to empirically measure its similarity to a reference corpus whose composition is known. In this paper we evaluate a number of measures of corpus similarity, including a method based on topic modelling which has not been previously evaluated for this task. To evaluate these methods we use known-similarity corpora that have been previously used for this purpose, as well as a number of newly-constructed known-similarity corpora targeting differences in genre, topic, time, and region. Our findings indicate that, overall, the topic modelling approach did not improve on a chi-square method that had previously been found to work well for measuring corpus similarity.
%U https://aclanthology.org/L16-1042
%P 273-279
Markdown (Informal)
[Evaluating a Topic Modelling Approach to Measuring Corpus Similarity](https://aclanthology.org/L16-1042) (Fothergill et al., LREC 2016)
ACL