@inproceedings{rahamim-etal-2023-text,
title = "Text Augmentation Using Dataset Reconstruction for Low-Resource Classification",
author = "Rahamim, Adir and
Uziel, Guy and
Goldbraich, Esther and
Anaby Tavor, Ateret",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.466",
doi = "10.18653/v1/2023.findings-acl.466",
pages = "7389--7402",
abstract = "In the deployment of real-world text classification models, label scarcity is a common problem and as the number of classes increases, this problem becomes even more complex. An approach to addressing this problem is by applying text augmentation methods. One of the more prominent methods involves using the text-generation capabilities of language models. In this paper, we propose Text AUgmentation by Dataset Reconstruction (TAU-DR), a novel method of data augmentation for text classification. We conduct experiments on several multi-class datasets, showing that our approach improves the current state-of-the-art techniques for data augmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahamim-etal-2023-text">
<titleInfo>
<title>Text Augmentation Using Dataset Reconstruction for Low-Resource Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adir</namePart>
<namePart type="family">Rahamim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Uziel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esther</namePart>
<namePart type="family">Goldbraich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ateret</namePart>
<namePart type="family">Anaby Tavor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the deployment of real-world text classification models, label scarcity is a common problem and as the number of classes increases, this problem becomes even more complex. An approach to addressing this problem is by applying text augmentation methods. One of the more prominent methods involves using the text-generation capabilities of language models. In this paper, we propose Text AUgmentation by Dataset Reconstruction (TAU-DR), a novel method of data augmentation for text classification. We conduct experiments on several multi-class datasets, showing that our approach improves the current state-of-the-art techniques for data augmentation.</abstract>
<identifier type="citekey">rahamim-etal-2023-text</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.466</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.466</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7389</start>
<end>7402</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Augmentation Using Dataset Reconstruction for Low-Resource Classification
%A Rahamim, Adir
%A Uziel, Guy
%A Goldbraich, Esther
%A Anaby Tavor, Ateret
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F rahamim-etal-2023-text
%X In the deployment of real-world text classification models, label scarcity is a common problem and as the number of classes increases, this problem becomes even more complex. An approach to addressing this problem is by applying text augmentation methods. One of the more prominent methods involves using the text-generation capabilities of language models. In this paper, we propose Text AUgmentation by Dataset Reconstruction (TAU-DR), a novel method of data augmentation for text classification. We conduct experiments on several multi-class datasets, showing that our approach improves the current state-of-the-art techniques for data augmentation.
%R 10.18653/v1/2023.findings-acl.466
%U https://aclanthology.org/2023.findings-acl.466
%U https://doi.org/10.18653/v1/2023.findings-acl.466
%P 7389-7402
Markdown (Informal)
[Text Augmentation Using Dataset Reconstruction for Low-Resource Classification](https://aclanthology.org/2023.findings-acl.466) (Rahamim et al., Findings 2023)
ACL