@inproceedings{romadhona-etal-2022-brcc,
title = "{BRCC} and {S}enti{B}ahasa{R}ojak: The First {B}ahasa Rojak Corpus for Pretraining and Sentiment Analysis Dataset",
author = "Romadhona, Nanda Putri and
Lu, Sin-En and
Lu, Bo-Han and
Tsai, Richard Tzong-Han",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.389",
pages = "4418--4428",
abstract = "Code-mixing refers to the mixed use of multiple languages. It is prevalent in multilingual societies and is also one of the most challenging natural language processing tasks. In this paper, we study Bahasa Rojak, a dialect popular in Malaysia that consists of English, Malay, and Chinese. Aiming to establish a model to deal with the code-mixing phenomena of Bahasa Rojak, we use data augmentation to automatically construct the first Bahasa Rojak corpus for pre-training language models, which we name the Bahasa Rojak Crawled Corpus (BRCC). We also develop a new pre-trained model called {``}Mixed XLM{''}. The model can tag the language of the input token automatically to process code-mixing input. Finally, to test the effectiveness of the Mixed XLM model pre-trained on BRCC for social media scenarios where code-mixing is found frequently, we compile a new Bahasa Rojak sentiment analysis dataset, SentiBahasaRojak, with a Kappa value of 0.77.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="romadhona-etal-2022-brcc">
<titleInfo>
<title>BRCC and SentiBahasaRojak: The First Bahasa Rojak Corpus for Pretraining and Sentiment Analysis Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nanda</namePart>
<namePart type="given">Putri</namePart>
<namePart type="family">Romadhona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sin-En</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo-Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">Tzong-Han</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-mixing refers to the mixed use of multiple languages. It is prevalent in multilingual societies and is also one of the most challenging natural language processing tasks. In this paper, we study Bahasa Rojak, a dialect popular in Malaysia that consists of English, Malay, and Chinese. Aiming to establish a model to deal with the code-mixing phenomena of Bahasa Rojak, we use data augmentation to automatically construct the first Bahasa Rojak corpus for pre-training language models, which we name the Bahasa Rojak Crawled Corpus (BRCC). We also develop a new pre-trained model called “Mixed XLM”. The model can tag the language of the input token automatically to process code-mixing input. Finally, to test the effectiveness of the Mixed XLM model pre-trained on BRCC for social media scenarios where code-mixing is found frequently, we compile a new Bahasa Rojak sentiment analysis dataset, SentiBahasaRojak, with a Kappa value of 0.77.</abstract>
<identifier type="citekey">romadhona-etal-2022-brcc</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.389</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4418</start>
<end>4428</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BRCC and SentiBahasaRojak: The First Bahasa Rojak Corpus for Pretraining and Sentiment Analysis Dataset
%A Romadhona, Nanda Putri
%A Lu, Sin-En
%A Lu, Bo-Han
%A Tsai, Richard Tzong-Han
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F romadhona-etal-2022-brcc
%X Code-mixing refers to the mixed use of multiple languages. It is prevalent in multilingual societies and is also one of the most challenging natural language processing tasks. In this paper, we study Bahasa Rojak, a dialect popular in Malaysia that consists of English, Malay, and Chinese. Aiming to establish a model to deal with the code-mixing phenomena of Bahasa Rojak, we use data augmentation to automatically construct the first Bahasa Rojak corpus for pre-training language models, which we name the Bahasa Rojak Crawled Corpus (BRCC). We also develop a new pre-trained model called “Mixed XLM”. The model can tag the language of the input token automatically to process code-mixing input. Finally, to test the effectiveness of the Mixed XLM model pre-trained on BRCC for social media scenarios where code-mixing is found frequently, we compile a new Bahasa Rojak sentiment analysis dataset, SentiBahasaRojak, with a Kappa value of 0.77.
%U https://aclanthology.org/2022.coling-1.389
%P 4418-4428
Markdown (Informal)
[BRCC and SentiBahasaRojak: The First Bahasa Rojak Corpus for Pretraining and Sentiment Analysis Dataset](https://aclanthology.org/2022.coling-1.389) (Romadhona et al., COLING 2022)
ACL