<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2024-partialformer">
    <titleInfo>
        <title>PartialFormer: Modeling Part Instead of Whole for Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tong</namePart>
        <namePart type="family">Zheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bei</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huiwen</namePart>
        <namePart type="family">Bao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiale</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weiqiao</namePart>
        <namePart type="family">Shan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tong</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">JingBo</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The design choices in Transformer feed-forward neural networks have resulted in significant computational and parameter overhead. In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often overlooked in previous architectures. Guided by this principle, we introduce PartialFormer, a parameter-efficient Transformer architecture utilizing multiple smaller FFNs to reduce parameters and computation while maintaining essential hidden dimensions. These smaller FFNs are integrated into a multi-head attention mechanism for effective collaboration. We also propose a tailored head scaling strategy to enhance PartialFormer’s capabilities. Furthermore, we present a residual-like attention calculation to improve depth scaling within PartialFormer. Extensive experiments on 9 translation tasks and 1 abstractive summarization task validate the effectiveness of our PartialFormer approach on machine translation and summarization tasks. Our code would be available at: https://github.com/zhengkid/PartialFormer.</abstract>
    <identifier type="citekey">zheng-etal-2024-partialformer</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-acl.434</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.434</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>7280</start>
            <end>7294</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PartialFormer: Modeling Part Instead of Whole for Machine Translation
%A Zheng, Tong
%A Li, Bei
%A Bao, Huiwen
%A Wang, Jiale
%A Shan, Weiqiao
%A Xiao, Tong
%A Zhu, JingBo
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zheng-etal-2024-partialformer
%X The design choices in Transformer feed-forward neural networks have resulted in significant computational and parameter overhead. In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often overlooked in previous architectures. Guided by this principle, we introduce PartialFormer, a parameter-efficient Transformer architecture utilizing multiple smaller FFNs to reduce parameters and computation while maintaining essential hidden dimensions. These smaller FFNs are integrated into a multi-head attention mechanism for effective collaboration. We also propose a tailored head scaling strategy to enhance PartialFormer’s capabilities. Furthermore, we present a residual-like attention calculation to improve depth scaling within PartialFormer. Extensive experiments on 9 translation tasks and 1 abstractive summarization task validate the effectiveness of our PartialFormer approach on machine translation and summarization tasks. Our code would be available at: https://github.com/zhengkid/PartialFormer.
%R 10.18653/v1/2024.findings-acl.434
%U https://aclanthology.org/2024.findings-acl.434
%U https://doi.org/10.18653/v1/2024.findings-acl.434
%P 7280-7294

Markdown (Informal)

[PartialFormer: Modeling Part Instead of Whole for Machine Translation](https://aclanthology.org/2024.findings-acl.434) (Zheng et al., Findings 2024)

• PartialFormer: Modeling Part Instead of Whole for Machine Translation (Zheng et al., Findings 2024)

ACL

• Tong Zheng, Bei Li, Huiwen Bao, Jiale Wang, Weiqiao Shan, Tong Xiao, and JingBo Zhu. 2024. PartialFormer: Modeling Part Instead of Whole for Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 7280–7294, Bangkok, Thailand. Association for Computational Linguistics.