@inproceedings{zhou-etal-2021-virtual,
title = "Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models",
author = "Zhou, Kun and
Zhao, Wayne Xin and
Wang, Sirui and
Zhang, Fuzheng and
Wu, Wei and
Wen, Ji-Rong",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.315",
doi = "10.18653/v1/2021.emnlp-main.315",
pages = "3875--3887",
abstract = "Recent works have shown that powerful pre-trained language models (PLM) can be fooled by small perturbations or intentional attacks. To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs. However, it is still challenging to augment semantically relevant examples with sufficient diversity. In this work, we present Virtual Data Augmentation (VDA), a general framework for robustly fine-tuning PLMs. Based on the original token embeddings, we construct a multinomial mixture for augmenting virtual data embeddings, where a masked language model guarantees the semantic relevance and the Gaussian noise provides the augmentation diversity. Furthermore, a regularized training strategy is proposed to balance the two aspects. Extensive experiments on six datasets show that our approach is able to improve the robustness of PLMs and alleviate the performance degradation under adversarial attacks. Our codes and data are publicly available at blue\url{https://github.com/RUCAIBox/VDA}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2021-virtual">
<titleInfo>
<title>Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wayne</namePart>
<namePart type="given">Xin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuzheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-Rong</namePart>
<namePart type="family">Wen</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>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</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">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent works have shown that powerful pre-trained language models (PLM) can be fooled by small perturbations or intentional attacks. To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs. However, it is still challenging to augment semantically relevant examples with sufficient diversity. In this work, we present Virtual Data Augmentation (VDA), a general framework for robustly fine-tuning PLMs. Based on the original token embeddings, we construct a multinomial mixture for augmenting virtual data embeddings, where a masked language model guarantees the semantic relevance and the Gaussian noise provides the augmentation diversity. Furthermore, a regularized training strategy is proposed to balance the two aspects. Extensive experiments on six datasets show that our approach is able to improve the robustness of PLMs and alleviate the performance degradation under adversarial attacks. Our codes and data are publicly available at bluehttps://github.com/RUCAIBox/VDA.</abstract>
<identifier type="citekey">zhou-etal-2021-virtual</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.315</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.315</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3875</start>
<end>3887</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models
%A Zhou, Kun
%A Zhao, Wayne Xin
%A Wang, Sirui
%A Zhang, Fuzheng
%A Wu, Wei
%A Wen, Ji-Rong
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F zhou-etal-2021-virtual
%X Recent works have shown that powerful pre-trained language models (PLM) can be fooled by small perturbations or intentional attacks. To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs. However, it is still challenging to augment semantically relevant examples with sufficient diversity. In this work, we present Virtual Data Augmentation (VDA), a general framework for robustly fine-tuning PLMs. Based on the original token embeddings, we construct a multinomial mixture for augmenting virtual data embeddings, where a masked language model guarantees the semantic relevance and the Gaussian noise provides the augmentation diversity. Furthermore, a regularized training strategy is proposed to balance the two aspects. Extensive experiments on six datasets show that our approach is able to improve the robustness of PLMs and alleviate the performance degradation under adversarial attacks. Our codes and data are publicly available at bluehttps://github.com/RUCAIBox/VDA.
%R 10.18653/v1/2021.emnlp-main.315
%U https://aclanthology.org/2021.emnlp-main.315
%U https://doi.org/10.18653/v1/2021.emnlp-main.315
%P 3875-3887
Markdown (Informal)
[Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models](https://aclanthology.org/2021.emnlp-main.315) (Zhou et al., EMNLP 2021)
ACL