<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vincent-etal-2023-mtcue">
    <titleInfo>
        <title>MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sebastian</namePart>
        <namePart type="family">Vincent</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Robert</namePart>
        <namePart type="family">Flynn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carolina</namePart>
        <namePart type="family">Scarton</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Efficient utilisation of both intra- and extra-textual context remains one of the critical gaps between machine and human translation. Existing research has primarily focused on providing individual, well-defined types of context in translation, such as the surrounding text or discrete external variables like the speaker’s gender. This work introduces MTCue, a novel neural machine translation (NMT) framework that interprets all context (including discrete variables) as text. MTCue learns an abstract representation of context, enabling transferability across different data settings and leveraging similar attributes in low-resource scenarios. With a focus on a dialogue domain with access to document and metadata context, we extensively evaluate MTCue in four language pairs in both translation directions. Our framework demonstrates significant improvements in translation quality over a parameter-matched non-contextual baseline, as measured by BLEU (+0.88) and Comet (+1.58). Moreover, MTCue significantly outperforms a “tagging” baseline at translating English text. Analysis reveals that the context encoder of MTCue learns a representation space that organises context based on specific attributes, such as formality, enabling effective zero-shot control. Pre-training on context embeddings also improves MTCue’s few-shot performance compared to the “tagging” baseline. Finally, an ablation study conducted on model components and contextual variables further supports the robustness of MTCue for context-based NMT.</abstract>
    <identifier type="citekey">vincent-etal-2023-mtcue</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.521</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.521</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>8210</start>
            <end>8226</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation
%A Vincent, Sebastian
%A Flynn, Robert
%A Scarton, Carolina
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F vincent-etal-2023-mtcue
%X Efficient utilisation of both intra- and extra-textual context remains one of the critical gaps between machine and human translation. Existing research has primarily focused on providing individual, well-defined types of context in translation, such as the surrounding text or discrete external variables like the speaker’s gender. This work introduces MTCue, a novel neural machine translation (NMT) framework that interprets all context (including discrete variables) as text. MTCue learns an abstract representation of context, enabling transferability across different data settings and leveraging similar attributes in low-resource scenarios. With a focus on a dialogue domain with access to document and metadata context, we extensively evaluate MTCue in four language pairs in both translation directions. Our framework demonstrates significant improvements in translation quality over a parameter-matched non-contextual baseline, as measured by BLEU (+0.88) and Comet (+1.58). Moreover, MTCue significantly outperforms a “tagging” baseline at translating English text. Analysis reveals that the context encoder of MTCue learns a representation space that organises context based on specific attributes, such as formality, enabling effective zero-shot control. Pre-training on context embeddings also improves MTCue’s few-shot performance compared to the “tagging” baseline. Finally, an ablation study conducted on model components and contextual variables further supports the robustness of MTCue for context-based NMT.
%R 10.18653/v1/2023.findings-acl.521
%U https://aclanthology.org/2023.findings-acl.521
%U https://doi.org/10.18653/v1/2023.findings-acl.521
%P 8210-8226

Markdown (Informal)

[MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation](https://aclanthology.org/2023.findings-acl.521) (Vincent et al., Findings 2023)

• MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation (Vincent et al., Findings 2023)

ACL

• Sebastian Vincent, Robert Flynn, and Carolina Scarton. 2023. MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8210–8226, Toronto, Canada. Association for Computational Linguistics.