@inproceedings{yoo-etal-2021-gpt3mix-leveraging,
title = "{GPT}3{M}ix: Leveraging Large-scale Language Models for Text Augmentation",
author = "Yoo, Kang Min and
Park, Dongju and
Kang, Jaewook and
Lee, Sang-Woo and
Park, Woomyoung",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.192",
doi = "10.18653/v1/2021.findings-emnlp.192",
pages = "2225--2239",
abstract = "Large-scale language models such as GPT-3 are excellent few-shot learners, allowing them to be controlled via natural text prompts. Recent studies report that prompt-based direct classification eliminates the need for fine-tuning but lacks data and inference scalability. This paper proposes a novel data augmentation technique that leverages large-scale language models to generate realistic text samples from a mixture of real samples. We also propose utilizing soft-labels predicted by the language models, effectively distilling knowledge from the large-scale language models and creating textual perturbations simultaneously. We perform data augmentation experiments on diverse classification tasks and show that our method hugely outperforms existing text augmentation methods. We also conduct experiments on our newly proposed benchmark to show that the augmentation effect is not only attributed to memorization. Further ablation studies and a qualitative analysis provide more insights into our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoo-etal-2021-gpt3mix-leveraging">
<titleInfo>
<title>GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation</title>
</titleInfo>
<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">Dongju</namePart>
<namePart type="family">Park</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>
<name type="personal">
<namePart type="given">Sang-Woo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Woomyoung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale language models such as GPT-3 are excellent few-shot learners, allowing them to be controlled via natural text prompts. Recent studies report that prompt-based direct classification eliminates the need for fine-tuning but lacks data and inference scalability. This paper proposes a novel data augmentation technique that leverages large-scale language models to generate realistic text samples from a mixture of real samples. We also propose utilizing soft-labels predicted by the language models, effectively distilling knowledge from the large-scale language models and creating textual perturbations simultaneously. We perform data augmentation experiments on diverse classification tasks and show that our method hugely outperforms existing text augmentation methods. We also conduct experiments on our newly proposed benchmark to show that the augmentation effect is not only attributed to memorization. Further ablation studies and a qualitative analysis provide more insights into our approach.</abstract>
<identifier type="citekey">yoo-etal-2021-gpt3mix-leveraging</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.192</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.192</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2225</start>
<end>2239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation
%A Yoo, Kang Min
%A Park, Dongju
%A Kang, Jaewook
%A Lee, Sang-Woo
%A Park, Woomyoung
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F yoo-etal-2021-gpt3mix-leveraging
%X Large-scale language models such as GPT-3 are excellent few-shot learners, allowing them to be controlled via natural text prompts. Recent studies report that prompt-based direct classification eliminates the need for fine-tuning but lacks data and inference scalability. This paper proposes a novel data augmentation technique that leverages large-scale language models to generate realistic text samples from a mixture of real samples. We also propose utilizing soft-labels predicted by the language models, effectively distilling knowledge from the large-scale language models and creating textual perturbations simultaneously. We perform data augmentation experiments on diverse classification tasks and show that our method hugely outperforms existing text augmentation methods. We also conduct experiments on our newly proposed benchmark to show that the augmentation effect is not only attributed to memorization. Further ablation studies and a qualitative analysis provide more insights into our approach.
%R 10.18653/v1/2021.findings-emnlp.192
%U https://aclanthology.org/2021.findings-emnlp.192
%U https://doi.org/10.18653/v1/2021.findings-emnlp.192
%P 2225-2239
Markdown (Informal)
[GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation](https://aclanthology.org/2021.findings-emnlp.192) (Yoo et al., Findings 2021)
ACL