@inproceedings{wilie-etal-2020-indonlu,
title = "{I}ndo{NLU}: Benchmark and Resources for Evaluating {I}ndonesian Natural Language Understanding",
author = "Wilie, Bryan and
Vincentio, Karissa and
Winata, Genta Indra and
Cahyawijaya, Samuel and
Li, Xiaohong and
Lim, Zhi Yuan and
Soleman, Sidik and
Mahendra, Rahmad and
Fung, Pascale and
Bahar, Syafri and
Purwarianti, Ayu",
editor = "Wong, Kam-Fai and
Knight, Kevin and
Wu, Hua",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.85",
doi = "10.18653/v1/2020.aacl-main.85",
pages = "843--857",
abstract = "Although Indonesian is known to be the fourth most frequently used language over the internet, the research progress on this language in natural language processing (NLP) is slow-moving due to a lack of available resources. In response, we introduce the first-ever vast resource for training, evaluation, and benchmarking on Indonesian natural language understanding (IndoNLU) tasks. IndoNLU includes twelve tasks, ranging from single sentence classification to pair-sentences sequence labeling with different levels of complexity. The datasets for the tasks lie in different domains and styles to ensure task diversity. We also provide a set of Indonesian pre-trained models (IndoBERT) trained from a large and clean Indonesian dataset (Indo4B) collected from publicly available sources such as social media texts, blogs, news, and websites. We release baseline models for all twelve tasks, as well as the framework for benchmark evaluation, thus enabling everyone to benchmark their system performances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wilie-etal-2020-indonlu">
<titleInfo>
<title>IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Wilie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karissa</namePart>
<namePart type="family">Vincentio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="given">Yuan</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sidik</namePart>
<namePart type="family">Soleman</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">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syafri</namePart>
<namePart type="family">Bahar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although Indonesian is known to be the fourth most frequently used language over the internet, the research progress on this language in natural language processing (NLP) is slow-moving due to a lack of available resources. In response, we introduce the first-ever vast resource for training, evaluation, and benchmarking on Indonesian natural language understanding (IndoNLU) tasks. IndoNLU includes twelve tasks, ranging from single sentence classification to pair-sentences sequence labeling with different levels of complexity. The datasets for the tasks lie in different domains and styles to ensure task diversity. We also provide a set of Indonesian pre-trained models (IndoBERT) trained from a large and clean Indonesian dataset (Indo4B) collected from publicly available sources such as social media texts, blogs, news, and websites. We release baseline models for all twelve tasks, as well as the framework for benchmark evaluation, thus enabling everyone to benchmark their system performances.</abstract>
<identifier type="citekey">wilie-etal-2020-indonlu</identifier>
<identifier type="doi">10.18653/v1/2020.aacl-main.85</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.85</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>843</start>
<end>857</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding
%A Wilie, Bryan
%A Vincentio, Karissa
%A Winata, Genta Indra
%A Cahyawijaya, Samuel
%A Li, Xiaohong
%A Lim, Zhi Yuan
%A Soleman, Sidik
%A Mahendra, Rahmad
%A Fung, Pascale
%A Bahar, Syafri
%A Purwarianti, Ayu
%Y Wong, Kam-Fai
%Y Knight, Kevin
%Y Wu, Hua
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F wilie-etal-2020-indonlu
%X Although Indonesian is known to be the fourth most frequently used language over the internet, the research progress on this language in natural language processing (NLP) is slow-moving due to a lack of available resources. In response, we introduce the first-ever vast resource for training, evaluation, and benchmarking on Indonesian natural language understanding (IndoNLU) tasks. IndoNLU includes twelve tasks, ranging from single sentence classification to pair-sentences sequence labeling with different levels of complexity. The datasets for the tasks lie in different domains and styles to ensure task diversity. We also provide a set of Indonesian pre-trained models (IndoBERT) trained from a large and clean Indonesian dataset (Indo4B) collected from publicly available sources such as social media texts, blogs, news, and websites. We release baseline models for all twelve tasks, as well as the framework for benchmark evaluation, thus enabling everyone to benchmark their system performances.
%R 10.18653/v1/2020.aacl-main.85
%U https://aclanthology.org/2020.aacl-main.85
%U https://doi.org/10.18653/v1/2020.aacl-main.85
%P 843-857
Markdown (Informal)
[IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding](https://aclanthology.org/2020.aacl-main.85) (Wilie et al., AACL 2020)
ACL
- Bryan Wilie, Karissa Vincentio, Genta Indra Winata, Samuel Cahyawijaya, Xiaohong Li, Zhi Yuan Lim, Sidik Soleman, Rahmad Mahendra, Pascale Fung, Syafri Bahar, and Ayu Purwarianti. 2020. IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 843–857, Suzhou, China. Association for Computational Linguistics.