@inproceedings{domingo-etal-2021-social,
title = "What is on Social Media that is not in {W}ord{N}et? A Preliminary Analysis on the {T}witter{AAE} Corpus",
author = "Domingo, Cecilia and
Gonzalez-Ferrero, Tatiana and
Gonzalez-Dios, Itziar",
editor = "Vossen, Piek and
Fellbaum, Christiane",
booktitle = "Proceedings of the 11th Global Wordnet Conference",
month = jan,
year = "2021",
address = "University of South Africa (UNISA)",
publisher = "Global Wordnet Association",
url = "https://aclanthology.org/2021.gwc-1.27",
pages = "234--242",
abstract = "Natural Language Processing tools and resources have been so far mainly created and trained for standard varieties of language. Nowadays, with the use of large amounts of data gathered from social media, other varieties and registers need to be processed, which may present other challenges and difficulties. In this work, we focus on English and we present a preliminary analysis by comparing the TwitterAAE corpus, which is annotated for ethnicity, and WordNet by quantifying and explaining the online language that WordNet misses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="domingo-etal-2021-social">
<titleInfo>
<title>What is on Social Media that is not in WordNet? A Preliminary Analysis on the TwitterAAE Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cecilia</namePart>
<namePart type="family">Domingo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Gonzalez-Ferrero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itziar</namePart>
<namePart type="family">Gonzalez-Dios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Global Wordnet Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christiane</namePart>
<namePart type="family">Fellbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Global Wordnet Association</publisher>
<place>
<placeTerm type="text">University of South Africa (UNISA)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural Language Processing tools and resources have been so far mainly created and trained for standard varieties of language. Nowadays, with the use of large amounts of data gathered from social media, other varieties and registers need to be processed, which may present other challenges and difficulties. In this work, we focus on English and we present a preliminary analysis by comparing the TwitterAAE corpus, which is annotated for ethnicity, and WordNet by quantifying and explaining the online language that WordNet misses.</abstract>
<identifier type="citekey">domingo-etal-2021-social</identifier>
<location>
<url>https://aclanthology.org/2021.gwc-1.27</url>
</location>
<part>
<date>2021-01</date>
<extent unit="page">
<start>234</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What is on Social Media that is not in WordNet? A Preliminary Analysis on the TwitterAAE Corpus
%A Domingo, Cecilia
%A Gonzalez-Ferrero, Tatiana
%A Gonzalez-Dios, Itziar
%Y Vossen, Piek
%Y Fellbaum, Christiane
%S Proceedings of the 11th Global Wordnet Conference
%D 2021
%8 January
%I Global Wordnet Association
%C University of South Africa (UNISA)
%F domingo-etal-2021-social
%X Natural Language Processing tools and resources have been so far mainly created and trained for standard varieties of language. Nowadays, with the use of large amounts of data gathered from social media, other varieties and registers need to be processed, which may present other challenges and difficulties. In this work, we focus on English and we present a preliminary analysis by comparing the TwitterAAE corpus, which is annotated for ethnicity, and WordNet by quantifying and explaining the online language that WordNet misses.
%U https://aclanthology.org/2021.gwc-1.27
%P 234-242
Markdown (Informal)
[What is on Social Media that is not in WordNet? A Preliminary Analysis on the TwitterAAE Corpus](https://aclanthology.org/2021.gwc-1.27) (Domingo et al., GWC 2021)
ACL