@inproceedings{park-etal-2023-hypert5,
title = "{H}yper{T}5: Towards Compute-Efficient {K}orean Language Modeling",
author = "Park, Dongju and
Ka, Soonwon and
Yoo, Kang Min and
Lee, Gichang and
Kang, Jaewook",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.40",
doi = "10.18653/v1/2023.acl-industry.40",
pages = "412--424",
abstract = "Pretraining and fine-tuning language models have become the standard practice in industrial natural language processing (NLP), but developing and deploying general-purpose language models without the abundant computation or data resources is a real-world issue faced by smaller organizations or communities whose main focus is languages with less accessible resources (e.g., non-English). This paper explores the sequence-to-sequence (seq2seq) language model architecture as a more practical and compute-efficient alternative to the decoder-oriented approach (e.g., GPT-3), accompanied by novel findings in compute-optimality analyses. We successfully trained billion-scale Korean-language seq2seq language models that strongly outperform other competitive models in Korean benchmarks. Moreover, we demonstrate that such language models can be more efficiently utilized by employing a heavy pre-finetuning strategy, by showcasing a case study on dialog-task adaptation. Our case study shows that adopting language models with more readily available domain-specific unlabeled data greatly improves fine-tuning data efficiency in low-resource settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2023-hypert5">
<titleInfo>
<title>HyperT5: Towards Compute-Efficient Korean Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongju</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soonwon</namePart>
<namePart type="family">Ka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="given">Min</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gichang</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaewook</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretraining and fine-tuning language models have become the standard practice in industrial natural language processing (NLP), but developing and deploying general-purpose language models without the abundant computation or data resources is a real-world issue faced by smaller organizations or communities whose main focus is languages with less accessible resources (e.g., non-English). This paper explores the sequence-to-sequence (seq2seq) language model architecture as a more practical and compute-efficient alternative to the decoder-oriented approach (e.g., GPT-3), accompanied by novel findings in compute-optimality analyses. We successfully trained billion-scale Korean-language seq2seq language models that strongly outperform other competitive models in Korean benchmarks. Moreover, we demonstrate that such language models can be more efficiently utilized by employing a heavy pre-finetuning strategy, by showcasing a case study on dialog-task adaptation. Our case study shows that adopting language models with more readily available domain-specific unlabeled data greatly improves fine-tuning data efficiency in low-resource settings.</abstract>
<identifier type="citekey">park-etal-2023-hypert5</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.40</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.40</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>412</start>
<end>424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HyperT5: Towards Compute-Efficient Korean Language Modeling
%A Park, Dongju
%A Ka, Soonwon
%A Yoo, Kang Min
%A Lee, Gichang
%A Kang, Jaewook
%Y Sitaram, Sunayana
%Y Beigman Klebanov, Beata
%Y Williams, Jason D.
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F park-etal-2023-hypert5
%X Pretraining and fine-tuning language models have become the standard practice in industrial natural language processing (NLP), but developing and deploying general-purpose language models without the abundant computation or data resources is a real-world issue faced by smaller organizations or communities whose main focus is languages with less accessible resources (e.g., non-English). This paper explores the sequence-to-sequence (seq2seq) language model architecture as a more practical and compute-efficient alternative to the decoder-oriented approach (e.g., GPT-3), accompanied by novel findings in compute-optimality analyses. We successfully trained billion-scale Korean-language seq2seq language models that strongly outperform other competitive models in Korean benchmarks. Moreover, we demonstrate that such language models can be more efficiently utilized by employing a heavy pre-finetuning strategy, by showcasing a case study on dialog-task adaptation. Our case study shows that adopting language models with more readily available domain-specific unlabeled data greatly improves fine-tuning data efficiency in low-resource settings.
%R 10.18653/v1/2023.acl-industry.40
%U https://aclanthology.org/2023.acl-industry.40
%U https://doi.org/10.18653/v1/2023.acl-industry.40
%P 412-424
Markdown (Informal)
[HyperT5: Towards Compute-Efficient Korean Language Modeling](https://aclanthology.org/2023.acl-industry.40) (Park et al., ACL 2023)
ACL
- Dongju Park, Soonwon Ka, Kang Min Yoo, Gichang Lee, and Jaewook Kang. 2023. HyperT5: Towards Compute-Efficient Korean Language Modeling. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 412–424, Toronto, Canada. Association for Computational Linguistics.