@inproceedings{mohammad-2020-nlp,
title = "{NLP} Scholar: A Dataset for Examining the State of {NLP} Research",
author = "Mohammad, Saif M.",
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-1.109",
pages = "868--877",
abstract = "Google Scholar is the largest web search engine for academic literature that also provides access to rich metadata associated with the papers. The ACL Anthology (AA) is the largest repository of articles on Natural Language Processing (NLP). We extracted information from AA for about 44 thousand NLP papers and identified authors who published at least three papers there. We then extracted citation information from Google Scholar for all their papers (not just their AA papers). This resulted in a dataset of 1.1 million papers and associated Google Scholar information. We aligned the information in the AA and Google Scholar datasets to create the NLP Scholar Dataset {--} a single unified source of information (from both AA and Google Scholar) for tens of thousands of NLP papers. It can be used to identify broad trends in productivity, focus, and impact of NLP research. We present here initial work on analyzing the volume of research in NLP over the years and identifying the most cited papers in NLP. We also list a number of additional potential applications.",
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="mohammad-2020-nlp">
<titleInfo>
<title>NLP Scholar: A Dataset for Examining the State of NLP Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</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>Google Scholar is the largest web search engine for academic literature that also provides access to rich metadata associated with the papers. The ACL Anthology (AA) is the largest repository of articles on Natural Language Processing (NLP). We extracted information from AA for about 44 thousand NLP papers and identified authors who published at least three papers there. We then extracted citation information from Google Scholar for all their papers (not just their AA papers). This resulted in a dataset of 1.1 million papers and associated Google Scholar information. We aligned the information in the AA and Google Scholar datasets to create the NLP Scholar Dataset – a single unified source of information (from both AA and Google Scholar) for tens of thousands of NLP papers. It can be used to identify broad trends in productivity, focus, and impact of NLP research. We present here initial work on analyzing the volume of research in NLP over the years and identifying the most cited papers in NLP. We also list a number of additional potential applications.</abstract>
<identifier type="citekey">mohammad-2020-nlp</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.109</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>868</start>
<end>877</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP Scholar: A Dataset for Examining the State of NLP Research
%A Mohammad, Saif M.
%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 mohammad-2020-nlp
%X Google Scholar is the largest web search engine for academic literature that also provides access to rich metadata associated with the papers. The ACL Anthology (AA) is the largest repository of articles on Natural Language Processing (NLP). We extracted information from AA for about 44 thousand NLP papers and identified authors who published at least three papers there. We then extracted citation information from Google Scholar for all their papers (not just their AA papers). This resulted in a dataset of 1.1 million papers and associated Google Scholar information. We aligned the information in the AA and Google Scholar datasets to create the NLP Scholar Dataset – a single unified source of information (from both AA and Google Scholar) for tens of thousands of NLP papers. It can be used to identify broad trends in productivity, focus, and impact of NLP research. We present here initial work on analyzing the volume of research in NLP over the years and identifying the most cited papers in NLP. We also list a number of additional potential applications.
%U https://aclanthology.org/2020.lrec-1.109
%P 868-877
Markdown (Informal)
[NLP Scholar: A Dataset for Examining the State of NLP Research](https://aclanthology.org/2020.lrec-1.109) (Mohammad, LREC 2020)
ACL