@inproceedings{winata-etal-2023-nusax,
title = "{N}usa{X}: Multilingual Parallel Sentiment Dataset for 10 {I}ndonesian Local Languages",
author = "Winata, Genta Indra and
Aji, Alham Fikri and
Cahyawijaya, Samuel and
Mahendra, Rahmad and
Koto, Fajri and
Romadhony, Ade and
Kurniawan, Kemal and
Moeljadi, David and
Prasojo, Radityo Eko and
Fung, Pascale and
Baldwin, Timothy and
Lau, Jey Han and
Sennrich, Rico and
Ruder, Sebastian",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.57",
doi = "10.18653/v1/2023.eacl-main.57",
pages = "815--834",
abstract = "Natural language processing (NLP) has a significant impact on society via technologies such as machine translation and search engines. Despite its success, NLP technology is only widely available for high-resource languages such as English and Chinese, while it remains inaccessible to many languages due to the unavailability of data resources and benchmarks. In this work, we focus on developing resources for languages in Indonesia. Despite being the second most linguistically diverse country, most languages in Indonesia are categorized as endangered and some are even extinct. We develop the first-ever parallel resource for 10 low-resource languages in Indonesia. Our resource includes sentiment and machine translation datasets, and bilingual lexicons. We provide extensive analyses and describe challenges for creating such resources. We hope this work can spark NLP research on Indonesian and other underrepresented languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winata-etal-2023-nusax">
<titleInfo>
<title>NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahmad</namePart>
<namePart type="family">Mahendra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ade</namePart>
<namePart type="family">Romadhony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Kurniawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Moeljadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radityo</namePart>
<namePart type="given">Eko</namePart>
<namePart type="family">Prasojo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jey</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language processing (NLP) has a significant impact on society via technologies such as machine translation and search engines. Despite its success, NLP technology is only widely available for high-resource languages such as English and Chinese, while it remains inaccessible to many languages due to the unavailability of data resources and benchmarks. In this work, we focus on developing resources for languages in Indonesia. Despite being the second most linguistically diverse country, most languages in Indonesia are categorized as endangered and some are even extinct. We develop the first-ever parallel resource for 10 low-resource languages in Indonesia. Our resource includes sentiment and machine translation datasets, and bilingual lexicons. We provide extensive analyses and describe challenges for creating such resources. We hope this work can spark NLP research on Indonesian and other underrepresented languages.</abstract>
<identifier type="citekey">winata-etal-2023-nusax</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.57</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.57</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>815</start>
<end>834</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages
%A Winata, Genta Indra
%A Aji, Alham Fikri
%A Cahyawijaya, Samuel
%A Mahendra, Rahmad
%A Koto, Fajri
%A Romadhony, Ade
%A Kurniawan, Kemal
%A Moeljadi, David
%A Prasojo, Radityo Eko
%A Fung, Pascale
%A Baldwin, Timothy
%A Lau, Jey Han
%A Sennrich, Rico
%A Ruder, Sebastian
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F winata-etal-2023-nusax
%X Natural language processing (NLP) has a significant impact on society via technologies such as machine translation and search engines. Despite its success, NLP technology is only widely available for high-resource languages such as English and Chinese, while it remains inaccessible to many languages due to the unavailability of data resources and benchmarks. In this work, we focus on developing resources for languages in Indonesia. Despite being the second most linguistically diverse country, most languages in Indonesia are categorized as endangered and some are even extinct. We develop the first-ever parallel resource for 10 low-resource languages in Indonesia. Our resource includes sentiment and machine translation datasets, and bilingual lexicons. We provide extensive analyses and describe challenges for creating such resources. We hope this work can spark NLP research on Indonesian and other underrepresented languages.
%R 10.18653/v1/2023.eacl-main.57
%U https://aclanthology.org/2023.eacl-main.57
%U https://doi.org/10.18653/v1/2023.eacl-main.57
%P 815-834
Markdown (Informal)
[NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages](https://aclanthology.org/2023.eacl-main.57) (Winata et al., EACL 2023)
ACL
- Genta Indra Winata, Alham Fikri Aji, Samuel Cahyawijaya, Rahmad Mahendra, Fajri Koto, Ade Romadhony, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Pascale Fung, Timothy Baldwin, Jey Han Lau, Rico Sennrich, and Sebastian Ruder. 2023. NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 815–834, Dubrovnik, Croatia. Association for Computational Linguistics.