@inproceedings{kementchedjhieva-chalkidis-2023-exploration,
title = "An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text",
author = "Kementchedjhieva, Yova and
Chalkidis, Ilias",
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.360",
doi = "10.18653/v1/2023.findings-acl.360",
pages = "5828--5843",
abstract = "Standard methods for multi-label text classification largely rely on encoder-only pre-trained language models, whereas encoder-decoder models have proven more effective in other classification tasks. In this study, we compare four methods for multi-label classification, two based on an encoder only, and two based on an encoder-decoder. We carry out experiments on four datasets{---}two in the legal domain and two in the biomedical domain, each with two levels of label granularity{---} and always depart from the same pre-trained model, T5. Our results show that encoder-decoder methods outperform encoder-only methods, with a growing advantage on more complex datasets and labeling schemes of finer granularity. Using encoder-decoder models in a non-autoregressive fashion, in particular, yields the best performance overall, so we further study this approach through ablations to better understand its strengths.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kementchedjhieva-chalkidis-2023-exploration">
<titleInfo>
<title>An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yova</namePart>
<namePart type="family">Kementchedjhieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</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>Standard methods for multi-label text classification largely rely on encoder-only pre-trained language models, whereas encoder-decoder models have proven more effective in other classification tasks. In this study, we compare four methods for multi-label classification, two based on an encoder only, and two based on an encoder-decoder. We carry out experiments on four datasets—two in the legal domain and two in the biomedical domain, each with two levels of label granularity— and always depart from the same pre-trained model, T5. Our results show that encoder-decoder methods outperform encoder-only methods, with a growing advantage on more complex datasets and labeling schemes of finer granularity. Using encoder-decoder models in a non-autoregressive fashion, in particular, yields the best performance overall, so we further study this approach through ablations to better understand its strengths.</abstract>
<identifier type="citekey">kementchedjhieva-chalkidis-2023-exploration</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.360</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.360</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5828</start>
<end>5843</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text
%A Kementchedjhieva, Yova
%A Chalkidis, Ilias
%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 kementchedjhieva-chalkidis-2023-exploration
%X Standard methods for multi-label text classification largely rely on encoder-only pre-trained language models, whereas encoder-decoder models have proven more effective in other classification tasks. In this study, we compare four methods for multi-label classification, two based on an encoder only, and two based on an encoder-decoder. We carry out experiments on four datasets—two in the legal domain and two in the biomedical domain, each with two levels of label granularity— and always depart from the same pre-trained model, T5. Our results show that encoder-decoder methods outperform encoder-only methods, with a growing advantage on more complex datasets and labeling schemes of finer granularity. Using encoder-decoder models in a non-autoregressive fashion, in particular, yields the best performance overall, so we further study this approach through ablations to better understand its strengths.
%R 10.18653/v1/2023.findings-acl.360
%U https://aclanthology.org/2023.findings-acl.360
%U https://doi.org/10.18653/v1/2023.findings-acl.360
%P 5828-5843
Markdown (Informal)
[An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text](https://aclanthology.org/2023.findings-acl.360) (Kementchedjhieva & Chalkidis, Findings 2023)
ACL