<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2020-multi">
    <titleInfo>
        <title>Multi-Unit Transformers for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jianhao</namePart>
        <namePart type="family">Yan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fandong</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Transformer models achieve remarkable success in Neural Machine Translation. Many efforts have been devoted to deepening the Transformer by stacking several units (i.e., a combination of Multihead Attentions and FFN) in a cascade, while the investigation over multiple parallel units draws little attention. In this paper, we propose the Multi-Unit Transformer (MUTE) , which aim to promote the expressiveness of the Transformer by introducing diverse and complementary units. Specifically, we use several parallel units and show that modeling with multiple units improves model performance and introduces diversity. Further, to better leverage the advantage of the multi-unit setting, we design biased module and sequential dependency that guide and encourage complementariness among different units. Experimental results on three machine translation tasks, the NIST Chinese-to-English, WMT’14 English-to-German and WMT’18 Chinese-to-English, show that the MUTE models significantly outperform the Transformer-Base, by up to +1.52, +1.90 and +1.10 BLEU points, with only a mild drop in inference speed (about 3.1%). In addition, our methods also surpass the Transformer-Big model, with only 54% of its parameters. These results demonstrate the effectiveness of the MUTE, as well as its efficiency in both the inference process and parameter usage.</abstract>
    <identifier type="citekey">yan-etal-2020-multi</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.77</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.77</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>1047</start>
            <end>1059</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Unit Transformers for Neural Machine Translation
%A Yan, Jianhao
%A Meng, Fandong
%A Zhou, Jie
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yan-etal-2020-multi
%X Transformer models achieve remarkable success in Neural Machine Translation. Many efforts have been devoted to deepening the Transformer by stacking several units (i.e., a combination of Multihead Attentions and FFN) in a cascade, while the investigation over multiple parallel units draws little attention. In this paper, we propose the Multi-Unit Transformer (MUTE) , which aim to promote the expressiveness of the Transformer by introducing diverse and complementary units. Specifically, we use several parallel units and show that modeling with multiple units improves model performance and introduces diversity. Further, to better leverage the advantage of the multi-unit setting, we design biased module and sequential dependency that guide and encourage complementariness among different units. Experimental results on three machine translation tasks, the NIST Chinese-to-English, WMT’14 English-to-German and WMT’18 Chinese-to-English, show that the MUTE models significantly outperform the Transformer-Base, by up to +1.52, +1.90 and +1.10 BLEU points, with only a mild drop in inference speed (about 3.1%). In addition, our methods also surpass the Transformer-Big model, with only 54% of its parameters. These results demonstrate the effectiveness of the MUTE, as well as its efficiency in both the inference process and parameter usage.
%R 10.18653/v1/2020.emnlp-main.77
%U https://aclanthology.org/2020.emnlp-main.77
%U https://doi.org/10.18653/v1/2020.emnlp-main.77
%P 1047-1059

Markdown (Informal)

[Multi-Unit Transformers for Neural Machine Translation](https://aclanthology.org/2020.emnlp-main.77) (Yan et al., EMNLP 2020)

• Multi-Unit Transformers for Neural Machine Translation (Yan et al., EMNLP 2020)

ACL

• Jianhao Yan, Fandong Meng, and Jie Zhou. 2020. Multi-Unit Transformers for Neural Machine Translation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1047–1059, Online. Association for Computational Linguistics.