<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pombal-etal-2026-context">
    <titleInfo>
        <title>A Context-aware Framework for Translation-mediated Conversations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">José</namePart>
        <namePart type="family">Pombal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sweta</namePart>
        <namePart type="family">Agrawal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emmanouil</namePart>
        <namePart type="family">Zaranis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Patrick</namePart>
        <namePart type="family">Fernandes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">André</namePart>
        <namePart type="given">F</namePart>
        <namePart type="given">T</namePart>
        <namePart type="family">Martins</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</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>Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation breakdown. A key issue is that current systems fail to incorporate the rich contextual information necessary to resolve ambiguities and omitted details, resulting in literal, inappropriate, or misaligned translations. In this work, we present a framework to improve large language model-based translation systems by incorporating contextual information in bilingual conversational settings during training and inference. We validate our proposed framework on two task-oriented domains: customer chat and user-assistant interaction. Across both settings, the system produced by our framework—TowerChat—consistently results in better translations than state-of-the-art systems like GPT-4o and TowerInstruct, as measured by multiple automatic translation quality metrics on several language pairs. We also show that the resulting model leverages context in an intended and interpretable way, improving consistency between the conveyed message and the generated translations.1</abstract>
    <identifier type="citekey">pombal-etal-2026-context</identifier>
    <identifier type="doi">10.1162/tacl.a.639</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.26/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>562</start>
            <end>587</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T A Context-aware Framework for Translation-mediated Conversations
%A Pombal, José
%A Agrawal, Sweta
%A Zaranis, Emmanouil
%A Fernandes, Patrick
%A Martins, André F. T.
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F pombal-etal-2026-context
%X Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation breakdown. A key issue is that current systems fail to incorporate the rich contextual information necessary to resolve ambiguities and omitted details, resulting in literal, inappropriate, or misaligned translations. In this work, we present a framework to improve large language model-based translation systems by incorporating contextual information in bilingual conversational settings during training and inference. We validate our proposed framework on two task-oriented domains: customer chat and user-assistant interaction. Across both settings, the system produced by our framework—TowerChat—consistently results in better translations than state-of-the-art systems like GPT-4o and TowerInstruct, as measured by multiple automatic translation quality metrics on several language pairs. We also show that the resulting model leverages context in an intended and interpretable way, improving consistency between the conveyed message and the generated translations.1
%R 10.1162/tacl.a.639
%U https://aclanthology.org/2026.tacl-1.26/
%U https://doi.org/10.1162/tacl.a.639
%P 562-587

Markdown (Informal)

[A Context-aware Framework for Translation-mediated Conversations](https://aclanthology.org/2026.tacl-1.26/) (Pombal et al., TACL 2026)

• A Context-aware Framework for Translation-mediated Conversations (Pombal et al., TACL 2026)

ACL

• José Pombal, Sweta Agrawal, Emmanouil Zaranis, Patrick Fernandes, and André F. T. Martins. 2026. A Context-aware Framework for Translation-mediated Conversations. Transactions of the Association for Computational Linguistics, 14:562–587.