@inproceedings{jiang-etal-2023-low,
title = "{``}Low-Resource{''} Text Classification: A Parameter-Free Classification Method with Compressors",
author = "Jiang, Zhiying and
Yang, Matthew and
Tsirlin, Mikhail and
Tang, Raphael and
Dai, Yiqin and
Lin, Jimmy",
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.426",
doi = "10.18653/v1/2023.findings-acl.426",
pages = "6810--6828",
abstract = "Deep neural networks (DNNs) are often used for text classification due to their high accuracy. However, DNNs can be computationally intensive, requiring millions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize, and to transfer to out-of-distribution (OOD) cases in practice. In this paper, we propose a non-parametric alternative to DNNs that{'}s easy, lightweight, and universal in text classification: a combination of a simple compressor like \textit{gzip} with a $k$-nearest-neighbor classifier. Without any training parameters, our method achieves results that are competitive with non-pretrained deep learning methods on six in-distribution datasets.It even outperforms BERT on all five OOD datasets, including four low-resource languages. Our method also excels in the few-shot setting, where labeled data are too scarce to train DNNs effectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2023-low">
<titleInfo>
<title>“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiying</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Tsirlin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqin</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimmy</namePart>
<namePart type="family">Lin</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>Deep neural networks (DNNs) are often used for text classification due to their high accuracy. However, DNNs can be computationally intensive, requiring millions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize, and to transfer to out-of-distribution (OOD) cases in practice. In this paper, we propose a non-parametric alternative to DNNs that’s easy, lightweight, and universal in text classification: a combination of a simple compressor like gzip with a k-nearest-neighbor classifier. Without any training parameters, our method achieves results that are competitive with non-pretrained deep learning methods on six in-distribution datasets.It even outperforms BERT on all five OOD datasets, including four low-resource languages. Our method also excels in the few-shot setting, where labeled data are too scarce to train DNNs effectively.</abstract>
<identifier type="citekey">jiang-etal-2023-low</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.426</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.426</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6810</start>
<end>6828</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors
%A Jiang, Zhiying
%A Yang, Matthew
%A Tsirlin, Mikhail
%A Tang, Raphael
%A Dai, Yiqin
%A Lin, Jimmy
%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 jiang-etal-2023-low
%X Deep neural networks (DNNs) are often used for text classification due to their high accuracy. However, DNNs can be computationally intensive, requiring millions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize, and to transfer to out-of-distribution (OOD) cases in practice. In this paper, we propose a non-parametric alternative to DNNs that’s easy, lightweight, and universal in text classification: a combination of a simple compressor like gzip with a k-nearest-neighbor classifier. Without any training parameters, our method achieves results that are competitive with non-pretrained deep learning methods on six in-distribution datasets.It even outperforms BERT on all five OOD datasets, including four low-resource languages. Our method also excels in the few-shot setting, where labeled data are too scarce to train DNNs effectively.
%R 10.18653/v1/2023.findings-acl.426
%U https://aclanthology.org/2023.findings-acl.426
%U https://doi.org/10.18653/v1/2023.findings-acl.426
%P 6810-6828
Markdown (Informal)
[“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors](https://aclanthology.org/2023.findings-acl.426) (Jiang et al., Findings 2023)
ACL