<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schmidt-etal-2022-non">
    <titleInfo>
        <title>Non-Autoregressive Neural Machine Translation: A Call for Clarity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Robin</namePart>
        <namePart type="family">Schmidt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Telmo</namePart>
        <namePart type="family">Pires</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stephan</namePart>
        <namePart type="family">Peitz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonas</namePart>
        <namePart type="family">Lööf</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>Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their translation quality still tends to be inferior to their autoregressive counterparts due to several issues involving output token interdependence. In this work, we take a step back and revisit several techniques that have been proposed for improving non-autoregressive translation models and compare their combined translation quality and speed implications under third-party testing environments. We provide novel insights for establishing strong baselines using length prediction or CTC-based architecture variants and contribute standardized BLEU, chrF++, and TER scores using sacreBLEU on four translation tasks, which crucially have been missing as inconsistencies in the use of tokenized BLEU lead to deviations of up to 1.7 BLEU points. Our open-sourced code is integrated into fairseq for reproducibility.</abstract>
    <identifier type="citekey">schmidt-etal-2022-non</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.179</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.179</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>2785</start>
            <end>2799</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Non-Autoregressive Neural Machine Translation: A Call for Clarity
%A Schmidt, Robin
%A Pires, Telmo
%A Peitz, Stephan
%A Lööf, Jonas
%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 schmidt-etal-2022-non
%X Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their translation quality still tends to be inferior to their autoregressive counterparts due to several issues involving output token interdependence. In this work, we take a step back and revisit several techniques that have been proposed for improving non-autoregressive translation models and compare their combined translation quality and speed implications under third-party testing environments. We provide novel insights for establishing strong baselines using length prediction or CTC-based architecture variants and contribute standardized BLEU, chrF++, and TER scores using sacreBLEU on four translation tasks, which crucially have been missing as inconsistencies in the use of tokenized BLEU lead to deviations of up to 1.7 BLEU points. Our open-sourced code is integrated into fairseq for reproducibility.
%R 10.18653/v1/2022.emnlp-main.179
%U https://aclanthology.org/2022.emnlp-main.179
%U https://doi.org/10.18653/v1/2022.emnlp-main.179
%P 2785-2799

Markdown (Informal)

[Non-Autoregressive Neural Machine Translation: A Call for Clarity](https://aclanthology.org/2022.emnlp-main.179) (Schmidt et al., EMNLP 2022)

• Non-Autoregressive Neural Machine Translation: A Call for Clarity (Schmidt et al., EMNLP 2022)

ACL

• Robin Schmidt, Telmo Pires, Stephan Peitz, and Jonas Lööf. 2022. Non-Autoregressive Neural Machine Translation: A Call for Clarity. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2785–2799, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.