@inproceedings{sun-etal-2020-mixup,
title = "Mixup-Transformer: Dynamic Data Augmentation for {NLP} Tasks",
author = "Sun, Lichao and
Xia, Congying and
Yin, Wenpeng and
Liang, Tingting and
Yu, Philip and
He, Lifang",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.305",
doi = "10.18653/v1/2020.coling-main.305",
pages = "3436--3440",
abstract = "Mixup is a latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this line of research, in this paper, we explore i) how to apply mixup to natural language processing tasks since text data can hardly be mixed in the raw format; ii) if mixup is still effective in transformer-based learning models,e.g., BERT.To achieve the goal, we incorporate mixup to transformer-based pre-trained architecture, named{``}mixup-transformer{''}, for a wide range of NLP tasks while keeping the whole end-to-end training system. We evaluate the proposed framework by running extensive experiments on the GLUEbenchmark. Furthermore, we also examine the performance of mixup-transformer in low-resource scenarios by reducing the training data with a certain ratio. Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2020-mixup">
<titleInfo>
<title>Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lichao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Congying</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenpeng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Mixup is a latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this line of research, in this paper, we explore i) how to apply mixup to natural language processing tasks since text data can hardly be mixed in the raw format; ii) if mixup is still effective in transformer-based learning models,e.g., BERT.To achieve the goal, we incorporate mixup to transformer-based pre-trained architecture, named“mixup-transformer”, for a wide range of NLP tasks while keeping the whole end-to-end training system. We evaluate the proposed framework by running extensive experiments on the GLUEbenchmark. Furthermore, we also examine the performance of mixup-transformer in low-resource scenarios by reducing the training data with a certain ratio. Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.</abstract>
<identifier type="citekey">sun-etal-2020-mixup</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.305</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.305</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3436</start>
<end>3440</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks
%A Sun, Lichao
%A Xia, Congying
%A Yin, Wenpeng
%A Liang, Tingting
%A Yu, Philip
%A He, Lifang
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F sun-etal-2020-mixup
%X Mixup is a latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this line of research, in this paper, we explore i) how to apply mixup to natural language processing tasks since text data can hardly be mixed in the raw format; ii) if mixup is still effective in transformer-based learning models,e.g., BERT.To achieve the goal, we incorporate mixup to transformer-based pre-trained architecture, named“mixup-transformer”, for a wide range of NLP tasks while keeping the whole end-to-end training system. We evaluate the proposed framework by running extensive experiments on the GLUEbenchmark. Furthermore, we also examine the performance of mixup-transformer in low-resource scenarios by reducing the training data with a certain ratio. Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.
%R 10.18653/v1/2020.coling-main.305
%U https://aclanthology.org/2020.coling-main.305
%U https://doi.org/10.18653/v1/2020.coling-main.305
%P 3436-3440
Markdown (Informal)
[Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks](https://aclanthology.org/2020.coling-main.305) (Sun et al., COLING 2020)
ACL
- Lichao Sun, Congying Xia, Wenpeng Yin, Tingting Liang, Philip Yu, and Lifang He. 2020. Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3436–3440, Barcelona, Spain (Online). International Committee on Computational Linguistics.