@inproceedings{saravanan-etal-2012-empirical,
title = "An Empirical Study of the Occurrence and Co-Occurrence of Named Entities in Natural Language Corpora",
author = "Saravanan, K and
Choudhury, Monojit and
Udupa, Raghavendra and
Kumaran, A",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/305_Paper.pdf",
pages = "3118--3125",
abstract = "Named Entities (NEs) that occur in natural language text are important especially due to the advent of social media, and they play a critical role in the development of many natural language technologies. In this paper, we systematically analyze the patterns of occurrence and co-occurrence of NEs in standard large English news corpora - providing valuable insight for the understanding of the corpus, and subsequently paving way for the development of technologies that rely critically on handling NEs. We use two distinctive approaches: normal statistical analysis that measure and report the occurrence patterns of NEs in terms of frequency, growth, etc., and a complex networks based analysis that measures the co-occurrence pattern in terms of connectivity, degree-distribution, small-world phenomenon, etc. Our analysis indicates that: (i) NEs form an open-set in corpora and grow linearly, (ii) presence of a kernel and peripheral NE's, with the large periphery occurring rarely, and (iii) a strong evidence of small-world phenomenon. Our findings may suggest effective ways for construction of NE lexicons to aid efficient development of several natural language technologies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saravanan-etal-2012-empirical">
<titleInfo>
<title>An Empirical Study of the Occurrence and Co-Occurrence of Named Entities in Natural Language Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="family">Saravanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghavendra</namePart>
<namePart type="family">Udupa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Kumaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entities (NEs) that occur in natural language text are important especially due to the advent of social media, and they play a critical role in the development of many natural language technologies. In this paper, we systematically analyze the patterns of occurrence and co-occurrence of NEs in standard large English news corpora - providing valuable insight for the understanding of the corpus, and subsequently paving way for the development of technologies that rely critically on handling NEs. We use two distinctive approaches: normal statistical analysis that measure and report the occurrence patterns of NEs in terms of frequency, growth, etc., and a complex networks based analysis that measures the co-occurrence pattern in terms of connectivity, degree-distribution, small-world phenomenon, etc. Our analysis indicates that: (i) NEs form an open-set in corpora and grow linearly, (ii) presence of a kernel and peripheral NE’s, with the large periphery occurring rarely, and (iii) a strong evidence of small-world phenomenon. Our findings may suggest effective ways for construction of NE lexicons to aid efficient development of several natural language technologies.</abstract>
<identifier type="citekey">saravanan-etal-2012-empirical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/305_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3118</start>
<end>3125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Study of the Occurrence and Co-Occurrence of Named Entities in Natural Language Corpora
%A Saravanan, K.
%A Choudhury, Monojit
%A Udupa, Raghavendra
%A Kumaran, A.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F saravanan-etal-2012-empirical
%X Named Entities (NEs) that occur in natural language text are important especially due to the advent of social media, and they play a critical role in the development of many natural language technologies. In this paper, we systematically analyze the patterns of occurrence and co-occurrence of NEs in standard large English news corpora - providing valuable insight for the understanding of the corpus, and subsequently paving way for the development of technologies that rely critically on handling NEs. We use two distinctive approaches: normal statistical analysis that measure and report the occurrence patterns of NEs in terms of frequency, growth, etc., and a complex networks based analysis that measures the co-occurrence pattern in terms of connectivity, degree-distribution, small-world phenomenon, etc. Our analysis indicates that: (i) NEs form an open-set in corpora and grow linearly, (ii) presence of a kernel and peripheral NE’s, with the large periphery occurring rarely, and (iii) a strong evidence of small-world phenomenon. Our findings may suggest effective ways for construction of NE lexicons to aid efficient development of several natural language technologies.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/305_Paper.pdf
%P 3118-3125
Markdown (Informal)
[An Empirical Study of the Occurrence and Co-Occurrence of Named Entities in Natural Language Corpora](http://www.lrec-conf.org/proceedings/lrec2012/pdf/305_Paper.pdf) (Saravanan et al., LREC 2012)
ACL