@inproceedings{zhang-etal-2023-long,
title = "Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions",
author = "Zhang, Ruohong and
Wang, Yau-Shian and
Yang, Yiming and
Yu, Donghan and
Vu, Tom and
Lei, Likun",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.81",
doi = "10.18653/v1/2023.findings-eacl.81",
pages = "1092--1106",
abstract = "Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions. This paper addresses the challenge of tail label prediction by leveraging the power of dense neural retrieval model in mapping input documents (as queries) to relevant label descriptions. To further enhance the quality of label descriptions, we propose to generate pseudo label descriptions from a trained bag-of-words (BoW) classifier, which demonstrates better classification performance under severe scarce data conditions. The proposed approach achieves the state-of-the-art (SOTA) performance of overall label prediction on XMTC benchmark datasets and especially outperforms the SOTA models in the tail label prediction. We also provide a theoretical analysis for relating the BoW and neural models w.r.t. performance lower bound.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-long">
<titleInfo>
<title>Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruohong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yau-Shian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Likun</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions. This paper addresses the challenge of tail label prediction by leveraging the power of dense neural retrieval model in mapping input documents (as queries) to relevant label descriptions. To further enhance the quality of label descriptions, we propose to generate pseudo label descriptions from a trained bag-of-words (BoW) classifier, which demonstrates better classification performance under severe scarce data conditions. The proposed approach achieves the state-of-the-art (SOTA) performance of overall label prediction on XMTC benchmark datasets and especially outperforms the SOTA models in the tail label prediction. We also provide a theoretical analysis for relating the BoW and neural models w.r.t. performance lower bound.</abstract>
<identifier type="citekey">zhang-etal-2023-long</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.81</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.81</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1092</start>
<end>1106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions
%A Zhang, Ruohong
%A Wang, Yau-Shian
%A Yang, Yiming
%A Yu, Donghan
%A Vu, Tom
%A Lei, Likun
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F zhang-etal-2023-long
%X Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions. This paper addresses the challenge of tail label prediction by leveraging the power of dense neural retrieval model in mapping input documents (as queries) to relevant label descriptions. To further enhance the quality of label descriptions, we propose to generate pseudo label descriptions from a trained bag-of-words (BoW) classifier, which demonstrates better classification performance under severe scarce data conditions. The proposed approach achieves the state-of-the-art (SOTA) performance of overall label prediction on XMTC benchmark datasets and especially outperforms the SOTA models in the tail label prediction. We also provide a theoretical analysis for relating the BoW and neural models w.r.t. performance lower bound.
%R 10.18653/v1/2023.findings-eacl.81
%U https://aclanthology.org/2023.findings-eacl.81
%U https://doi.org/10.18653/v1/2023.findings-eacl.81
%P 1092-1106
Markdown (Informal)
[Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions](https://aclanthology.org/2023.findings-eacl.81) (Zhang et al., Findings 2023)
ACL