@inproceedings{herrera-etal-2022-tweettaglish,
title = "{T}weet{T}aglish: A Dataset for Investigating {T}agalog-{E}nglish Code-Switching",
author = "Herrera, Megan and
Aich, Ankit and
Parde, Natalie",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.225",
pages = "2090--2097",
abstract = "Deploying recent natural language processing innovations to low-resource settings allows for state-of-the-art research findings and applications to be accessed across cultural and linguistic borders. One low-resource setting of increasing interest is code-switching, the phenomenon of combining, swapping, or alternating the use of two or more languages in continuous dialogue. In this paper, we introduce a large dataset (20k+ instances) to facilitate investigation of Tagalog-English code-switching, which has become a popular mode of discourse in Philippine culture. Tagalog is an Austronesian language and former official language of the Philippines spoken by over 23 million people worldwide, but it and Tagalog-English are under-represented in NLP research and practice. We describe our methods for data collection, as well as our labeling procedures. We analyze our resulting dataset, and finally conclude by providing results from a proof-of-concept regression task to establish dataset validity, achieving a strong performance benchmark (R2=0.797-0.909; RMSE=0.068-0.057).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="herrera-etal-2022-tweettaglish">
<titleInfo>
<title>TweetTaglish: A Dataset for Investigating Tagalog-English Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Megan</namePart>
<namePart type="family">Herrera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Aich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>Deploying recent natural language processing innovations to low-resource settings allows for state-of-the-art research findings and applications to be accessed across cultural and linguistic borders. One low-resource setting of increasing interest is code-switching, the phenomenon of combining, swapping, or alternating the use of two or more languages in continuous dialogue. In this paper, we introduce a large dataset (20k+ instances) to facilitate investigation of Tagalog-English code-switching, which has become a popular mode of discourse in Philippine culture. Tagalog is an Austronesian language and former official language of the Philippines spoken by over 23 million people worldwide, but it and Tagalog-English are under-represented in NLP research and practice. We describe our methods for data collection, as well as our labeling procedures. We analyze our resulting dataset, and finally conclude by providing results from a proof-of-concept regression task to establish dataset validity, achieving a strong performance benchmark (R2=0.797-0.909; RMSE=0.068-0.057).</abstract>
<identifier type="citekey">herrera-etal-2022-tweettaglish</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.225</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2090</start>
<end>2097</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TweetTaglish: A Dataset for Investigating Tagalog-English Code-Switching
%A Herrera, Megan
%A Aich, Ankit
%A Parde, Natalie
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F herrera-etal-2022-tweettaglish
%X Deploying recent natural language processing innovations to low-resource settings allows for state-of-the-art research findings and applications to be accessed across cultural and linguistic borders. One low-resource setting of increasing interest is code-switching, the phenomenon of combining, swapping, or alternating the use of two or more languages in continuous dialogue. In this paper, we introduce a large dataset (20k+ instances) to facilitate investigation of Tagalog-English code-switching, which has become a popular mode of discourse in Philippine culture. Tagalog is an Austronesian language and former official language of the Philippines spoken by over 23 million people worldwide, but it and Tagalog-English are under-represented in NLP research and practice. We describe our methods for data collection, as well as our labeling procedures. We analyze our resulting dataset, and finally conclude by providing results from a proof-of-concept regression task to establish dataset validity, achieving a strong performance benchmark (R2=0.797-0.909; RMSE=0.068-0.057).
%U https://aclanthology.org/2022.lrec-1.225
%P 2090-2097
Markdown (Informal)
[TweetTaglish: A Dataset for Investigating Tagalog-English Code-Switching](https://aclanthology.org/2022.lrec-1.225) (Herrera et al., LREC 2022)
ACL