<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-hypoformer">
    <titleInfo>
        <title>Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sunzhu</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peng</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guobing</namePart>
        <namePart type="family">Gan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiuqing</namePart>
        <namePart type="family">Lv</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benyou</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junqiu</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xin</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Transformer has been demonstrated effective in Neural Machine Translation (NMT). However, it is memory-consuming and time-consuming in edge devices, resulting in some difficulties for real-time feedback. To compress and accelerate Transformer, we propose a Hybrid Tensor-Train (HTT) decomposition, which retains full rank and meanwhile reduces operations and parameters. A Transformer using HTT, named Hypoformer, consistently and notably outperforms the recent light-weight SOTA methods on three standard translation tasks under different parameter and speed scales. In extreme low resource scenarios, Hypoformer has 7.1 points absolute improvement in BLEU and 1.27 X speedup than vanilla Transformer on IWSLT‘14 De-En task.</abstract>
    <identifier type="citekey">li-etal-2022-hypoformer</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.475</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.475/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>7056</start>
            <end>7068</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation
%A Li, Sunzhu
%A Zhang, Peng
%A Gan, Guobing
%A Lv, Xiuqing
%A Wang, Benyou
%A Wei, Junqiu
%A Jiang, Xin
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F li-etal-2022-hypoformer
%X Transformer has been demonstrated effective in Neural Machine Translation (NMT). However, it is memory-consuming and time-consuming in edge devices, resulting in some difficulties for real-time feedback. To compress and accelerate Transformer, we propose a Hybrid Tensor-Train (HTT) decomposition, which retains full rank and meanwhile reduces operations and parameters. A Transformer using HTT, named Hypoformer, consistently and notably outperforms the recent light-weight SOTA methods on three standard translation tasks under different parameter and speed scales. In extreme low resource scenarios, Hypoformer has 7.1 points absolute improvement in BLEU and 1.27 X speedup than vanilla Transformer on IWSLT‘14 De-En task.
%R 10.18653/v1/2022.emnlp-main.475
%U https://aclanthology.org/2022.emnlp-main.475/
%U https://doi.org/10.18653/v1/2022.emnlp-main.475
%P 7056-7068

Markdown (Informal)

[Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation](https://aclanthology.org/2022.emnlp-main.475/) (Li et al., EMNLP 2022)

• Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation (Li et al., EMNLP 2022)

ACL

• Sunzhu Li, Peng Zhang, Guobing Gan, Xiuqing Lv, Benyou Wang, Junqiu Wei, and Xin Jiang. 2022. Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7056–7068, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.