<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ge-etal-2022-edgeformer">
    <titleInfo>
        <title>EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Ge</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Si-Qing</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Furu</namePart>
        <namePart type="family">Wei</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>We introduce EdgeFormer – a parameter-efficient Transformer for on-device seq2seq generation under the strict computation and memory constraints. Compared with the previous parameter-efficient Transformers, EdgeFormer applies two novel principles for cost-effective parameterization, allowing it to perform better given the same parameter budget; moreover, EdgeFormer is further enhanced by layer adaptation innovation that is proposed for improving the network with shared layers. Extensive experiments show EdgeFormer can effectively outperform previous parameter-efficient Transformer baselines and achieve competitive results under both the computation and memory constraints. Given the promising results, we release EdgeLM – the pretrained version of EdgeFormer, which is the first publicly available pretrained on-device seq2seq model that can be easily fine-tuned for seq2seq tasks with strong results, facilitating on-device seq2seq generation in practice.</abstract>
    <identifier type="citekey">ge-etal-2022-edgeformer</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.741</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.741</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>10786</start>
            <end>10798</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation
%A Ge, Tao
%A Chen, Si-Qing
%A Wei, Furu
%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 ge-etal-2022-edgeformer
%X We introduce EdgeFormer – a parameter-efficient Transformer for on-device seq2seq generation under the strict computation and memory constraints. Compared with the previous parameter-efficient Transformers, EdgeFormer applies two novel principles for cost-effective parameterization, allowing it to perform better given the same parameter budget; moreover, EdgeFormer is further enhanced by layer adaptation innovation that is proposed for improving the network with shared layers. Extensive experiments show EdgeFormer can effectively outperform previous parameter-efficient Transformer baselines and achieve competitive results under both the computation and memory constraints. Given the promising results, we release EdgeLM – the pretrained version of EdgeFormer, which is the first publicly available pretrained on-device seq2seq model that can be easily fine-tuned for seq2seq tasks with strong results, facilitating on-device seq2seq generation in practice.
%R 10.18653/v1/2022.emnlp-main.741
%U https://aclanthology.org/2022.emnlp-main.741
%U https://doi.org/10.18653/v1/2022.emnlp-main.741
%P 10786-10798

Markdown (Informal)

[EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation](https://aclanthology.org/2022.emnlp-main.741) (Ge et al., EMNLP 2022)

• EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation (Ge et al., EMNLP 2022)

ACL

• Tao Ge, Si-Qing Chen, and Furu Wei. 2022. EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10786–10798, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.