@inproceedings{li-etal-2023-towards-better,
title = "Towards Better Representations for Multi-Label Text Classification with Multi-granularity Information",
author = "Li, Fangfang and
Su, Puzhen and
Duan, Junwen and
Xiao, Weidong",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.635",
doi = "10.18653/v1/2023.findings-emnlp.635",
pages = "9470--9480",
abstract = "Multi-label text classification (MLTC) aims to assign multiple labels to a given text. Previous works have focused on text representation learning and label correlations modeling using pre-trained language models (PLMs). However, studies have shown that PLMs generate word frequency-oriented text representations, causing texts with different labels to be closely distributed in a narrow region, which is difficult to classify. To address this, we present a novel framework $\textbf{CL}$($\underline{C}$ontrastive $\underline{L}$earning)-$\textbf{MIL}$ ($\underline{M}$ulti-granularity $\underline{I}$nformation $\underline{L}$earning) to refine the text representation for MLTC task. We first use contrastive learning to generate uniform initial text representation and incorporate label frequency implicitly. Then, we design a multi-task learning module to integrate multi-granularity (diverse text-labels correlations, label-label relations and label frequency) information into text representations, enhancing their discriminative ability. Experimental results demonstrate the complementarity of the modules in CL-MIL, improving the quality of text representations and yielding stable and competitive improvements for MLTC.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-towards-better">
<titleInfo>
<title>Towards Better Representations for Multi-Label Text Classification with Multi-granularity Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fangfang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Puzhen</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junwen</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weidong</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-label text classification (MLTC) aims to assign multiple labels to a given text. Previous works have focused on text representation learning and label correlations modeling using pre-trained language models (PLMs). However, studies have shown that PLMs generate word frequency-oriented text representations, causing texts with different labels to be closely distributed in a narrow region, which is difficult to classify. To address this, we present a novel framework CL(\underlineContrastive \underlineLearning)-MIL (\underlineMulti-granularity \underlineInformation \underlineLearning) to refine the text representation for MLTC task. We first use contrastive learning to generate uniform initial text representation and incorporate label frequency implicitly. Then, we design a multi-task learning module to integrate multi-granularity (diverse text-labels correlations, label-label relations and label frequency) information into text representations, enhancing their discriminative ability. Experimental results demonstrate the complementarity of the modules in CL-MIL, improving the quality of text representations and yielding stable and competitive improvements for MLTC.</abstract>
<identifier type="citekey">li-etal-2023-towards-better</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.635</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.635</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>9470</start>
<end>9480</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Better Representations for Multi-Label Text Classification with Multi-granularity Information
%A Li, Fangfang
%A Su, Puzhen
%A Duan, Junwen
%A Xiao, Weidong
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F li-etal-2023-towards-better
%X Multi-label text classification (MLTC) aims to assign multiple labels to a given text. Previous works have focused on text representation learning and label correlations modeling using pre-trained language models (PLMs). However, studies have shown that PLMs generate word frequency-oriented text representations, causing texts with different labels to be closely distributed in a narrow region, which is difficult to classify. To address this, we present a novel framework CL(\underlineContrastive \underlineLearning)-MIL (\underlineMulti-granularity \underlineInformation \underlineLearning) to refine the text representation for MLTC task. We first use contrastive learning to generate uniform initial text representation and incorporate label frequency implicitly. Then, we design a multi-task learning module to integrate multi-granularity (diverse text-labels correlations, label-label relations and label frequency) information into text representations, enhancing their discriminative ability. Experimental results demonstrate the complementarity of the modules in CL-MIL, improving the quality of text representations and yielding stable and competitive improvements for MLTC.
%R 10.18653/v1/2023.findings-emnlp.635
%U https://aclanthology.org/2023.findings-emnlp.635
%U https://doi.org/10.18653/v1/2023.findings-emnlp.635
%P 9470-9480
Markdown (Informal)
[Towards Better Representations for Multi-Label Text Classification with Multi-granularity Information](https://aclanthology.org/2023.findings-emnlp.635) (Li et al., Findings 2023)
ACL