<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-multi-granularity">
    <titleInfo>
        <title>Multi-Granularity Optimization for Non-Autoregressive Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yafu</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Leyang</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongjing</namePart>
        <namePart type="family">Yin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Zhang</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>Despite low latency, non-autoregressive machine translation (NAT) suffers severe performance deterioration due to the naive independence assumption. This assumption is further strengthened by cross-entropy loss, which encourages a strict match between the hypothesis and the reference token by token. To alleviate this issue, we propose multi-granularity optimization for NAT, which collects model behaviours on translation segments of various granularities and integrates feedback for backpropagation. Experiments on four WMT benchmarks show that the proposed method significantly outperforms the baseline models trained with cross-entropy loss, and achieves the best performance on WMT’16 En⇔Ro and highly competitive results on WMT’14 En⇔De for fully non-autoregressive translation.</abstract>
    <identifier type="citekey">li-etal-2022-multi-granularity</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.339</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.339</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>5073</start>
            <end>5084</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Granularity Optimization for Non-Autoregressive Translation
%A Li, Yafu
%A Cui, Leyang
%A Yin, Yongjing
%A Zhang, Yue
%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-multi-granularity
%X Despite low latency, non-autoregressive machine translation (NAT) suffers severe performance deterioration due to the naive independence assumption. This assumption is further strengthened by cross-entropy loss, which encourages a strict match between the hypothesis and the reference token by token. To alleviate this issue, we propose multi-granularity optimization for NAT, which collects model behaviours on translation segments of various granularities and integrates feedback for backpropagation. Experiments on four WMT benchmarks show that the proposed method significantly outperforms the baseline models trained with cross-entropy loss, and achieves the best performance on WMT’16 En⇔Ro and highly competitive results on WMT’14 En⇔De for fully non-autoregressive translation.
%R 10.18653/v1/2022.emnlp-main.339
%U https://aclanthology.org/2022.emnlp-main.339
%U https://doi.org/10.18653/v1/2022.emnlp-main.339
%P 5073-5084

Markdown (Informal)

[Multi-Granularity Optimization for Non-Autoregressive Translation](https://aclanthology.org/2022.emnlp-main.339) (Li et al., EMNLP 2022)

• Multi-Granularity Optimization for Non-Autoregressive Translation (Li et al., EMNLP 2022)

ACL

• Yafu Li, Leyang Cui, Yongjing Yin, and Yue Zhang. 2022. Multi-Granularity Optimization for Non-Autoregressive Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5073–5084, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.