<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kano-etal-2022-simultaneous">
    <titleInfo>
        <title>Simultaneous Neural Machine Translation with Prefix Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yasumasa</namePart>
        <namePart type="family">Kano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Katsuhito</namePart>
        <namePart type="family">Sudoh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Satoshi</namePart>
        <namePart type="family">Nakamura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Simultaneous translation is a task that requires starting translation before the speaker has finished speaking, so we face a trade-off between latency and accuracy. In this work, we focus on prefix-to-prefix translation and propose a method to extract alignment between bilingual prefix pairs. We use the alignment to segment a streaming input and fine-tune a translation model. The proposed method demonstrated higher BLEU than those of baselines in low latency ranges in our experiments on the IWSLT simultaneous translation benchmark.</abstract>
    <identifier type="citekey">kano-etal-2022-simultaneous</identifier>
    <identifier type="doi">10.18653/v1/2022.iwslt-1.3</identifier>
    <location>
        <url>https://aclanthology.org/2022.iwslt-1.3</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>22</start>
            <end>31</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Simultaneous Neural Machine Translation with Prefix Alignment
%A Kano, Yasumasa
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%S Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland (in-person and online)
%F kano-etal-2022-simultaneous
%X Simultaneous translation is a task that requires starting translation before the speaker has finished speaking, so we face a trade-off between latency and accuracy. In this work, we focus on prefix-to-prefix translation and propose a method to extract alignment between bilingual prefix pairs. We use the alignment to segment a streaming input and fine-tune a translation model. The proposed method demonstrated higher BLEU than those of baselines in low latency ranges in our experiments on the IWSLT simultaneous translation benchmark.
%R 10.18653/v1/2022.iwslt-1.3
%U https://aclanthology.org/2022.iwslt-1.3
%U https://doi.org/10.18653/v1/2022.iwslt-1.3
%P 22-31

Markdown (Informal)

[Simultaneous Neural Machine Translation with Prefix Alignment](https://aclanthology.org/2022.iwslt-1.3) (Kano et al., IWSLT 2022)

• Simultaneous Neural Machine Translation with Prefix Alignment (Kano et al., IWSLT 2022)

ACL

• Yasumasa Kano, Katsuhito Sudoh, and Satoshi Nakamura. 2022. Simultaneous Neural Machine Translation with Prefix Alignment. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 22–31, Dublin, Ireland (in-person and online). Association for Computational Linguistics.