Segmentation-Free Streaming Machine Translation

Javier Iranzo-Sánchez; Jorge Iranzo-Sánchez; Adrià Gimenez; Jorge Civera; Alfons Juan

doi:10.1162/tacl_a_00691

Segmentation-Free Streaming Machine Translation

Javier Iranzo-Sánchez, Jorge Iranzo-Sánchez, Adrià Giménez, Jorge Civera, Alfons Juan

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until after the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model.1

Anthology ID:: 2024.tacl-1.61
Volume:: Transactions of the Association for Computational Linguistics, Volume 12
Month:
Year:: 2024
Address:: Cambridge, MA
Venue:: TACL
SIG:
Publisher:: MIT Press
Note:
Pages:: 1104–1121
Language:
URL:: https://aclanthology.org/2024.tacl-1.61/
DOI:: 10.1162/tacl_a_00691
Bibkey:
Cite (ACL):: Javier Iranzo-Sánchez, Jorge Iranzo-Sánchez, Adrià Giménez, Jorge Civera, and Alfons Juan. 2024. Segmentation-Free Streaming Machine Translation. Transactions of the Association for Computational Linguistics, 12:1104–1121.
Cite (Informal):: Segmentation-Free Streaming Machine Translation (Iranzo-Sánchez et al., TACL 2024)
Copy Citation:
PDF:: https://aclanthology.org/2024.tacl-1.61.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@article{iranzo-sanchez-etal-2024-segmentation,
    title = "Segmentation-Free Streaming Machine Translation",
    author = "Iranzo-S{\'a}nchez, Javier  and
      Iranzo-S{\'a}nchez, Jorge  and
      Gim{\'e}nez, Adri{\`a}  and
      Civera, Jorge  and
      Juan, Alfons",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "12",
    year = "2024",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2024.tacl-1.61/",
    doi = "10.1162/tacl_a_00691",
    pages = "1104--1121",
    abstract = "Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until after the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model.1"
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iranzo-sanchez-etal-2024-segmentation">
    <titleInfo>
        <title>Segmentation-Free Streaming Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Javier</namePart>
        <namePart type="family">Iranzo-Sánchez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jorge</namePart>
        <namePart type="family">Iranzo-Sánchez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adrià</namePart>
        <namePart type="family">Giménez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jorge</namePart>
        <namePart type="family">Civera</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alfons</namePart>
        <namePart type="family">Juan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until after the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model.1</abstract>
    <identifier type="citekey">iranzo-sanchez-etal-2024-segmentation</identifier>
    <identifier type="doi">10.1162/tacl_a_00691</identifier>
    <location>
        <url>https://aclanthology.org/2024.tacl-1.61/</url>
    </location>
    <part>
        <date>2024</date>
        <detail type="volume"><number>12</number></detail>
        <extent unit="page">
            <start>1104</start>
            <end>1121</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Journal Article
%T Segmentation-Free Streaming Machine Translation
%A Iranzo-Sánchez, Javier
%A Iranzo-Sánchez, Jorge
%A Giménez, Adrià
%A Civera, Jorge
%A Juan, Alfons
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F iranzo-sanchez-etal-2024-segmentation
%X Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until after the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model.1
%R 10.1162/tacl_a_00691
%U https://aclanthology.org/2024.tacl-1.61/
%U https://doi.org/10.1162/tacl_a_00691
%P 1104-1121

Download as File

Markdown (Informal)

[Segmentation-Free Streaming Machine Translation](https://aclanthology.org/2024.tacl-1.61/) (Iranzo-Sánchez et al., TACL 2024)

Segmentation-Free Streaming Machine Translation (Iranzo-Sánchez et al., TACL 2024)

ACL

Javier Iranzo-Sánchez, Jorge Iranzo-Sánchez, Adrià Giménez, Jorge Civera, and Alfons Juan. 2024. Segmentation-Free Streaming Machine Translation. Transactions of the Association for Computational Linguistics, 12:1104–1121.