@inproceedings{khatuya-etal-2025-label,
title = "Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification",
author = "Khatuya, Subhendu and
Naidu, Shashwat and
Ghosh, Saptarshi and
Goyal, Pawan and
Ganguly, Niloy",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1145/",
doi = "10.18653/v1/2025.findings-acl.1145",
pages = "22286--22298",
ISBN = "979-8-89176-256-5",
abstract = "The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model framework for multi-label text classification. Instead of treating labels as mere atomic symbols, our approach utilizes predefined label descriptions and is trained to generate these descriptions based on the input text. During inference, the generated descriptions are matched to the predefined labels using a finetuned sentence transformer. We integrate this with a dual-objective loss function, combining cross-entropy loss and cosine similarity of the generated sentences with the predefined target descriptions, ensuring both semantic alignment and accuracy. Our proposed model LAGAMC stands out for its parameter efficiency and versatility across diverse datasets, making it well-suited for practical applications. We demonstrate the effectiveness of our proposed model by achieving new state-of-the-art performances across all evaluated datasets, surpassing several strong baselines. We achieve improvements of 13.94 {\%} in Micro-F1 and 24.85 {\%} in Macro-F1 compared to the closest baseline across all datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khatuya-etal-2025-label">
<titleInfo>
<title>Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Subhendu</namePart>
<namePart type="family">Khatuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashwat</namePart>
<namePart type="family">Naidu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saptarshi</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloy</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model framework for multi-label text classification. Instead of treating labels as mere atomic symbols, our approach utilizes predefined label descriptions and is trained to generate these descriptions based on the input text. During inference, the generated descriptions are matched to the predefined labels using a finetuned sentence transformer. We integrate this with a dual-objective loss function, combining cross-entropy loss and cosine similarity of the generated sentences with the predefined target descriptions, ensuring both semantic alignment and accuracy. Our proposed model LAGAMC stands out for its parameter efficiency and versatility across diverse datasets, making it well-suited for practical applications. We demonstrate the effectiveness of our proposed model by achieving new state-of-the-art performances across all evaluated datasets, surpassing several strong baselines. We achieve improvements of 13.94 % in Micro-F1 and 24.85 % in Macro-F1 compared to the closest baseline across all datasets.</abstract>
<identifier type="citekey">khatuya-etal-2025-label</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1145</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1145/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22286</start>
<end>22298</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification
%A Khatuya, Subhendu
%A Naidu, Shashwat
%A Ghosh, Saptarshi
%A Goyal, Pawan
%A Ganguly, Niloy
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F khatuya-etal-2025-label
%X The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model framework for multi-label text classification. Instead of treating labels as mere atomic symbols, our approach utilizes predefined label descriptions and is trained to generate these descriptions based on the input text. During inference, the generated descriptions are matched to the predefined labels using a finetuned sentence transformer. We integrate this with a dual-objective loss function, combining cross-entropy loss and cosine similarity of the generated sentences with the predefined target descriptions, ensuring both semantic alignment and accuracy. Our proposed model LAGAMC stands out for its parameter efficiency and versatility across diverse datasets, making it well-suited for practical applications. We demonstrate the effectiveness of our proposed model by achieving new state-of-the-art performances across all evaluated datasets, surpassing several strong baselines. We achieve improvements of 13.94 % in Micro-F1 and 24.85 % in Macro-F1 compared to the closest baseline across all datasets.
%R 10.18653/v1/2025.findings-acl.1145
%U https://aclanthology.org/2025.findings-acl.1145/
%U https://doi.org/10.18653/v1/2025.findings-acl.1145
%P 22286-22298
Markdown (Informal)
[Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification](https://aclanthology.org/2025.findings-acl.1145/) (Khatuya et al., Findings 2025)
ACL