@inproceedings{mohammad-2020-wordwars,
title = "{W}ord{W}ars: A Dataset to Examine the Natural Selection of Words",
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-1.377",
pages = "3087--3095",
abstract = "There is a growing body of work on how word meaning changes over time: mutation. In contrast, there is very little work on how different words compete to represent the same meaning, and how the degree of success of words in that competition changes over time: natural selection. We present a new dataset, WordWars, with historical frequency data from the early 1800s to the early 2000s for monosemous English words in over 5000 synsets. We explore three broad questions with the dataset: (1) what is the degree to which predominant words in these synsets have changed, (2) how do prominent word features such as frequency, length, and concreteness impact natural selection, and (3) what are the differences between the predominant words of the 2000s and the predominant words of early 1800s. We show that close to one third of the synsets undergo a change in the predominant word in this time period. Manual annotation of these pairs shows that about 15{\%} of these are orthographic variations, 25{\%} involve affix changes, and 60{\%} have completely different roots. We find that frequency, length, and concreteness all impact natural selection, albeit in different ways.",
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-wordwars">
<titleInfo>
<title>WordWars: A Dataset to Examine the Natural Selection of Words</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>There is a growing body of work on how word meaning changes over time: mutation. In contrast, there is very little work on how different words compete to represent the same meaning, and how the degree of success of words in that competition changes over time: natural selection. We present a new dataset, WordWars, with historical frequency data from the early 1800s to the early 2000s for monosemous English words in over 5000 synsets. We explore three broad questions with the dataset: (1) what is the degree to which predominant words in these synsets have changed, (2) how do prominent word features such as frequency, length, and concreteness impact natural selection, and (3) what are the differences between the predominant words of the 2000s and the predominant words of early 1800s. We show that close to one third of the synsets undergo a change in the predominant word in this time period. Manual annotation of these pairs shows that about 15% of these are orthographic variations, 25% involve affix changes, and 60% have completely different roots. We find that frequency, length, and concreteness all impact natural selection, albeit in different ways.</abstract>
<identifier type="citekey">mohammad-2020-wordwars</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.377</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3087</start>
<end>3095</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WordWars: A Dataset to Examine the Natural Selection of Words
%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-wordwars
%X There is a growing body of work on how word meaning changes over time: mutation. In contrast, there is very little work on how different words compete to represent the same meaning, and how the degree of success of words in that competition changes over time: natural selection. We present a new dataset, WordWars, with historical frequency data from the early 1800s to the early 2000s for monosemous English words in over 5000 synsets. We explore three broad questions with the dataset: (1) what is the degree to which predominant words in these synsets have changed, (2) how do prominent word features such as frequency, length, and concreteness impact natural selection, and (3) what are the differences between the predominant words of the 2000s and the predominant words of early 1800s. We show that close to one third of the synsets undergo a change in the predominant word in this time period. Manual annotation of these pairs shows that about 15% of these are orthographic variations, 25% involve affix changes, and 60% have completely different roots. We find that frequency, length, and concreteness all impact natural selection, albeit in different ways.
%U https://aclanthology.org/2020.lrec-1.377
%P 3087-3095
Markdown (Informal)
[WordWars: A Dataset to Examine the Natural Selection of Words](https://aclanthology.org/2020.lrec-1.377) (Mohammad, LREC 2020)
ACL