@inproceedings{chen-liu-2022-rethinking,
title = "Rethinking Data Augmentation in Text-to-text Paradigm",
author = "Chen, Yanan and
Liu, Yang",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.99",
pages = "1157--1162",
abstract = "As manually labelling data can be costly, some recent studies tend to augment the training data for improving the generalization power of machine learning models, known as \textit{data augmentation} (DA). With the arise of pre-trained language models (PLMs), some recent works on DA try to synthesize new samples benefiting from the knowledge learned from PLM{'}s pre-training. Along the same direction, we in this paper propose to integrate text-to-text language models and construct a new two-phase framework for augmentation: 1) a fine-tuning phase where PLMs are well adapted to downstream classification with the help of two novel schemes, and 2) a generation phase where the fine-tuned models are leveraged to create new samples for performance lifting. This paradigm opens up a new way of designing fine-tuning scheme to better serve DA in an easy-to-implement manner, and can be easily extended to other desired tasks. We evaluate our proposal on two public classification datasets and demonstrate its effectiveness with remarkable gains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-liu-2022-rethinking">
<titleInfo>
<title>Rethinking Data Augmentation in Text-to-text Paradigm</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As manually labelling data can be costly, some recent studies tend to augment the training data for improving the generalization power of machine learning models, known as data augmentation (DA). With the arise of pre-trained language models (PLMs), some recent works on DA try to synthesize new samples benefiting from the knowledge learned from PLM’s pre-training. Along the same direction, we in this paper propose to integrate text-to-text language models and construct a new two-phase framework for augmentation: 1) a fine-tuning phase where PLMs are well adapted to downstream classification with the help of two novel schemes, and 2) a generation phase where the fine-tuned models are leveraged to create new samples for performance lifting. This paradigm opens up a new way of designing fine-tuning scheme to better serve DA in an easy-to-implement manner, and can be easily extended to other desired tasks. We evaluate our proposal on two public classification datasets and demonstrate its effectiveness with remarkable gains.</abstract>
<identifier type="citekey">chen-liu-2022-rethinking</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.99</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>1157</start>
<end>1162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Data Augmentation in Text-to-text Paradigm
%A Chen, Yanan
%A Liu, Yang
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F chen-liu-2022-rethinking
%X As manually labelling data can be costly, some recent studies tend to augment the training data for improving the generalization power of machine learning models, known as data augmentation (DA). With the arise of pre-trained language models (PLMs), some recent works on DA try to synthesize new samples benefiting from the knowledge learned from PLM’s pre-training. Along the same direction, we in this paper propose to integrate text-to-text language models and construct a new two-phase framework for augmentation: 1) a fine-tuning phase where PLMs are well adapted to downstream classification with the help of two novel schemes, and 2) a generation phase where the fine-tuned models are leveraged to create new samples for performance lifting. This paradigm opens up a new way of designing fine-tuning scheme to better serve DA in an easy-to-implement manner, and can be easily extended to other desired tasks. We evaluate our proposal on two public classification datasets and demonstrate its effectiveness with remarkable gains.
%U https://aclanthology.org/2022.coling-1.99
%P 1157-1162
Markdown (Informal)
[Rethinking Data Augmentation in Text-to-text Paradigm](https://aclanthology.org/2022.coling-1.99) (Chen & Liu, COLING 2022)
ACL
- Yanan Chen and Yang Liu. 2022. Rethinking Data Augmentation in Text-to-text Paradigm. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1157–1162, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.