@inproceedings{wu-etal-2022-text,
title = "Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks",
author = "Wu, Xing and
Gao, Chaochen and
Lin, Meng and
Zang, Liangjun and
Hu, Songlin",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.97/",
doi = "10.18653/v1/2022.acl-short.97",
pages = "871--875",
abstract = "Before entering the neural network, a token needs to be converted to its one-hot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained from the pre-trained masked language model, which can be seen as a more informative augmented substitution to the one-hot representation. We propose an efficient data augmentation method, dub as text smoothing, by converting a sentence from its one-hot representation to controllable smoothed representation. We evaluate text smoothing on different datasets in a low-resource regime. Experimental results show that text smoothing outperforms various mainstream data augmentation methods by a substantial margin. Moreover, text smoothing can be combined with these data augmentation methods to achieve better performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2022-text">
<titleInfo>
<title>Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaochen</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangjun</namePart>
<namePart type="family">Zang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songlin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Before entering the neural network, a token needs to be converted to its one-hot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained from the pre-trained masked language model, which can be seen as a more informative augmented substitution to the one-hot representation. We propose an efficient data augmentation method, dub as text smoothing, by converting a sentence from its one-hot representation to controllable smoothed representation. We evaluate text smoothing on different datasets in a low-resource regime. Experimental results show that text smoothing outperforms various mainstream data augmentation methods by a substantial margin. Moreover, text smoothing can be combined with these data augmentation methods to achieve better performance.</abstract>
<identifier type="citekey">wu-etal-2022-text</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.97</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.97/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>871</start>
<end>875</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks
%A Wu, Xing
%A Gao, Chaochen
%A Lin, Meng
%A Zang, Liangjun
%A Hu, Songlin
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F wu-etal-2022-text
%X Before entering the neural network, a token needs to be converted to its one-hot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained from the pre-trained masked language model, which can be seen as a more informative augmented substitution to the one-hot representation. We propose an efficient data augmentation method, dub as text smoothing, by converting a sentence from its one-hot representation to controllable smoothed representation. We evaluate text smoothing on different datasets in a low-resource regime. Experimental results show that text smoothing outperforms various mainstream data augmentation methods by a substantial margin. Moreover, text smoothing can be combined with these data augmentation methods to achieve better performance.
%R 10.18653/v1/2022.acl-short.97
%U https://aclanthology.org/2022.acl-short.97/
%U https://doi.org/10.18653/v1/2022.acl-short.97
%P 871-875
Markdown (Informal)
[Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks](https://aclanthology.org/2022.acl-short.97/) (Wu et al., ACL 2022)
ACL