@inproceedings{trye-etal-2019-maori,
title = "{M}{\=a}{o}ri Loanwords: A Corpus of {N}ew {Z}ealand {E}nglish Tweets",
author = "Trye, David and
Calude, Andreea and
Bravo-Marquez, Felipe and
Keegan, Te Taka",
editor = "Alva-Manchego, Fernando and
Choi, Eunsol and
Khashabi, Daniel",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-2018",
doi = "10.18653/v1/P19-2018",
pages = "136--142",
abstract = "M{\=a}ori loanwords are widely used in New Zealand English for various social functions by New Zealanders within and outside of the M{\=a}ori community. Motivated by the lack of linguistic resources for studying how M{\=a}ori loanwords are used in social media, we present a new corpus of New Zealand English tweets. We collected tweets containing selected M{\=a}ori words that are likely to be known by New Zealanders who do not speak M{\=a}ori. Since over 30{\%} of these words turned out to be irrelevant, we manually annotated a sample of our tweets into relevant and irrelevant categories. This data was used to train machine learning models to automatically filter out irrelevant tweets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trye-etal-2019-maori">
<titleInfo>
<title>Māori Loanwords: A Corpus of New Zealand English Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Trye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreea</namePart>
<namePart type="family">Calude</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Bravo-Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Te</namePart>
<namePart type="given">Taka</namePart>
<namePart type="family">Keegan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Khashabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Māori loanwords are widely used in New Zealand English for various social functions by New Zealanders within and outside of the Māori community. Motivated by the lack of linguistic resources for studying how Māori loanwords are used in social media, we present a new corpus of New Zealand English tweets. We collected tweets containing selected Māori words that are likely to be known by New Zealanders who do not speak Māori. Since over 30% of these words turned out to be irrelevant, we manually annotated a sample of our tweets into relevant and irrelevant categories. This data was used to train machine learning models to automatically filter out irrelevant tweets.</abstract>
<identifier type="citekey">trye-etal-2019-maori</identifier>
<identifier type="doi">10.18653/v1/P19-2018</identifier>
<location>
<url>https://aclanthology.org/P19-2018</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>136</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Māori Loanwords: A Corpus of New Zealand English Tweets
%A Trye, David
%A Calude, Andreea
%A Bravo-Marquez, Felipe
%A Keegan, Te Taka
%Y Alva-Manchego, Fernando
%Y Choi, Eunsol
%Y Khashabi, Daniel
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F trye-etal-2019-maori
%X Māori loanwords are widely used in New Zealand English for various social functions by New Zealanders within and outside of the Māori community. Motivated by the lack of linguistic resources for studying how Māori loanwords are used in social media, we present a new corpus of New Zealand English tweets. We collected tweets containing selected Māori words that are likely to be known by New Zealanders who do not speak Māori. Since over 30% of these words turned out to be irrelevant, we manually annotated a sample of our tweets into relevant and irrelevant categories. This data was used to train machine learning models to automatically filter out irrelevant tweets.
%R 10.18653/v1/P19-2018
%U https://aclanthology.org/P19-2018
%U https://doi.org/10.18653/v1/P19-2018
%P 136-142
Markdown (Informal)
[Māori Loanwords: A Corpus of New Zealand English Tweets](https://aclanthology.org/P19-2018) (Trye et al., ACL 2019)
ACL
- David Trye, Andreea Calude, Felipe Bravo-Marquez, and Te Taka Keegan. 2019. Māori Loanwords: A Corpus of New Zealand English Tweets. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 136–142, Florence, Italy. Association for Computational Linguistics.