@inproceedings{wibowo-etal-2024-copal,
title = "{COPAL}-{ID}: {I}ndonesian Language Reasoning with Local Culture and Nuances",
author = "Wibowo, Haryo and
Fuadi, Erland and
Nityasya, Made and
Prasojo, Radityo Eko and
Aji, Alham",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.77",
pages = "1404--1422",
abstract = "We present COPAL-ID, a novel, public Indonesian language common sense reasoning dataset. Unlike the previous Indonesian COPA dataset (XCOPA-ID), COPAL-ID incorporates Indonesian local and cultural nuances, and therefore, provides a more natural portrayal of day-to-day causal reasoning within the Indonesian cultural sphere. Professionally written by natives from scratch, COPAL-ID is more fluent and free from awkward phrases, unlike the translated XCOPA-ID. In addition, we present COPALID in both standard Indonesian and in Jakartan Indonesian{--}a dialect commonly used in daily conversation. COPAL-ID poses a greater challenge for existing open-sourced and closedstate-of-the-art multilingual language models, yet is trivially easy for humans. Our findings suggest that general multilingual models struggle to perform well, achieving 66.91{\%} accuracy on COPAL-ID. South-East Asian-specific models achieve slightly better performance of 73.88{\%} accuracy. Yet, this number still falls short of near-perfect human performance. This shows that these language models are still way behind in comprehending the local nuances of Indonesian.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wibowo-etal-2024-copal">
<titleInfo>
<title>COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haryo</namePart>
<namePart type="family">Wibowo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erland</namePart>
<namePart type="family">Fuadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Made</namePart>
<namePart type="family">Nityasya</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">Alham</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present COPAL-ID, a novel, public Indonesian language common sense reasoning dataset. Unlike the previous Indonesian COPA dataset (XCOPA-ID), COPAL-ID incorporates Indonesian local and cultural nuances, and therefore, provides a more natural portrayal of day-to-day causal reasoning within the Indonesian cultural sphere. Professionally written by natives from scratch, COPAL-ID is more fluent and free from awkward phrases, unlike the translated XCOPA-ID. In addition, we present COPALID in both standard Indonesian and in Jakartan Indonesian–a dialect commonly used in daily conversation. COPAL-ID poses a greater challenge for existing open-sourced and closedstate-of-the-art multilingual language models, yet is trivially easy for humans. Our findings suggest that general multilingual models struggle to perform well, achieving 66.91% accuracy on COPAL-ID. South-East Asian-specific models achieve slightly better performance of 73.88% accuracy. Yet, this number still falls short of near-perfect human performance. This shows that these language models are still way behind in comprehending the local nuances of Indonesian.</abstract>
<identifier type="citekey">wibowo-etal-2024-copal</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.77</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1404</start>
<end>1422</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances
%A Wibowo, Haryo
%A Fuadi, Erland
%A Nityasya, Made
%A Prasojo, Radityo Eko
%A Aji, Alham
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wibowo-etal-2024-copal
%X We present COPAL-ID, a novel, public Indonesian language common sense reasoning dataset. Unlike the previous Indonesian COPA dataset (XCOPA-ID), COPAL-ID incorporates Indonesian local and cultural nuances, and therefore, provides a more natural portrayal of day-to-day causal reasoning within the Indonesian cultural sphere. Professionally written by natives from scratch, COPAL-ID is more fluent and free from awkward phrases, unlike the translated XCOPA-ID. In addition, we present COPALID in both standard Indonesian and in Jakartan Indonesian–a dialect commonly used in daily conversation. COPAL-ID poses a greater challenge for existing open-sourced and closedstate-of-the-art multilingual language models, yet is trivially easy for humans. Our findings suggest that general multilingual models struggle to perform well, achieving 66.91% accuracy on COPAL-ID. South-East Asian-specific models achieve slightly better performance of 73.88% accuracy. Yet, this number still falls short of near-perfect human performance. This shows that these language models are still way behind in comprehending the local nuances of Indonesian.
%U https://aclanthology.org/2024.naacl-long.77
%P 1404-1422
Markdown (Informal)
[COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances](https://aclanthology.org/2024.naacl-long.77) (Wibowo et al., NAACL 2024)
ACL
- Haryo Wibowo, Erland Fuadi, Made Nityasya, Radityo Eko Prasojo, and Alham Aji. 2024. COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1404–1422, Mexico City, Mexico. Association for Computational Linguistics.