<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kreutzer-etal-2020-inference">
    <titleInfo>
        <title>Inference Strategies for Machine Translation with Conditional Masking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Julia</namePart>
        <namePart type="family">Kreutzer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">George</namePart>
        <namePart type="family">Foster</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Colin</namePart>
        <namePart type="family">Cherry</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>Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clear what the best inference strategy is. We formulate masked inference as a factorization of conditional probabilities of partial sequences, show that this does not harm performance, and investigate a number of simple heuristics motivated by this perspective. We identify a thresholding strategy that has advantages over the standard “mask-predict” algorithm, and provide analyses of its behavior on machine translation tasks.</abstract>
    <identifier type="citekey">kreutzer-etal-2020-inference</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.465</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.465</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>5774</start>
            <end>5782</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Inference Strategies for Machine Translation with Conditional Masking
%A Kreutzer, Julia
%A Foster, George
%A Cherry, Colin
%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 kreutzer-etal-2020-inference
%X Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clear what the best inference strategy is. We formulate masked inference as a factorization of conditional probabilities of partial sequences, show that this does not harm performance, and investigate a number of simple heuristics motivated by this perspective. We identify a thresholding strategy that has advantages over the standard “mask-predict” algorithm, and provide analyses of its behavior on machine translation tasks.
%R 10.18653/v1/2020.emnlp-main.465
%U https://aclanthology.org/2020.emnlp-main.465
%U https://doi.org/10.18653/v1/2020.emnlp-main.465
%P 5774-5782

Markdown (Informal)

[Inference Strategies for Machine Translation with Conditional Masking](https://aclanthology.org/2020.emnlp-main.465) (Kreutzer et al., EMNLP 2020)

• Inference Strategies for Machine Translation with Conditional Masking (Kreutzer et al., EMNLP 2020)

ACL

• Julia Kreutzer, George Foster, and Colin Cherry. 2020. Inference Strategies for Machine Translation with Conditional Masking. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5774–5782, Online. Association for Computational Linguistics.