<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guan-etal-2026-dart">
    <titleInfo>
        <title>DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Boyu</namePart>
        <namePart type="family">Guan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chuang</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chengqing</namePart>
        <namePart type="family">Zong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Video-guided Machine Translation (VMT) seeks to enhance translation quality by incorporating contextual information derived from paired short video clips. However, many VMT samples are text-sufficient; even when visual information is needed, only minimal cues are required. Aiming to tackle these issues, we propose a novel framework **DART** (**D**isambiguation-**A**ware **R**easoning for Video-guided Machine **T**ranslation). Reinforcement learning is used to incorporate multimodal large language models’ multimodal reasoning into VMT. The model dynamically switches between text-only processing and multimodal integration, contingent on the necessity of visual disambiguation. Furthermore, we present **TVRF** (**T**ranslation-oriented **V**ideo **R**elevance **F**iltering), a systematic pipeline for constructing training data based on multimodal relevance to translation. This pipeline filters samples where video information is translation-relevant, mitigating training collapse caused by video-irrelevant data in conventional VMT. Experimental results show that our approach improves multimodal information utilization in VMT, yielding gains in both translation quality and computational efficiency.</abstract>
    <identifier type="citekey">guan-etal-2026-dart</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.352/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>7752</start>
            <end>7772</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation
%A Guan, Boyu
%A Han, Chuang
%A Zhao, Yang
%A Zong, Chengqing
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F guan-etal-2026-dart
%X Video-guided Machine Translation (VMT) seeks to enhance translation quality by incorporating contextual information derived from paired short video clips. However, many VMT samples are text-sufficient; even when visual information is needed, only minimal cues are required. Aiming to tackle these issues, we propose a novel framework **DART** (**D**isambiguation-**A**ware **R**easoning for Video-guided Machine **T**ranslation). Reinforcement learning is used to incorporate multimodal large language models’ multimodal reasoning into VMT. The model dynamically switches between text-only processing and multimodal integration, contingent on the necessity of visual disambiguation. Furthermore, we present **TVRF** (**T**ranslation-oriented **V**ideo **R**elevance **F**iltering), a systematic pipeline for constructing training data based on multimodal relevance to translation. This pipeline filters samples where video information is translation-relevant, mitigating training collapse caused by video-irrelevant data in conventional VMT. Experimental results show that our approach improves multimodal information utilization in VMT, yielding gains in both translation quality and computational efficiency.
%U https://aclanthology.org/2026.acl-long.352/
%P 7752-7772

Markdown (Informal)

[DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation](https://aclanthology.org/2026.acl-long.352/) (Guan et al., ACL 2026)

• DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation (Guan et al., ACL 2026)

ACL

• Boyu Guan, Chuang Han, Yang Zhao, and Chengqing Zong. 2026. DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7752–7772, San Diego, California, United States. Association for Computational Linguistics.