@inproceedings{hatami-etal-2025-leveraging,
title = "Leveraging Visual Scene Graph to Enhance Translation Quality in Multimodal Machine Translation",
author = "Hatami, Ali and
Arcan, Mihael and
Buitelaar, Paul",
editor = "Bouillon, Pierrette and
Gerlach, Johanna and
Girletti, Sabrina and
Volkart, Lise and
Rubino, Raphael and
Sennrich, Rico and
Farinha, Ana C. and
Gaido, Marco and
Daems, Joke and
Kenny, Dorothy and
Moniz, Helena and
Szoc, Sara",
booktitle = "Proceedings of Machine Translation Summit XX: Volume 1",
month = jun,
year = "2025",
address = "Geneva, Switzerland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2025.mtsummit-1.27/",
pages = "353--364",
ISBN = "978-2-9701897-0-1",
abstract = "Despite significant advancements in Multimodal Machine Translation, understanding and effectively utilising visual scenes within multimodal models remains a complex challenge. Extracting comprehensive and relevant visual features requires extensive and detailed input data to ensure the model accurately captures objects, their attributes, and relationships within a scene. In this paper, we explore using visual scene graphs extracted from images to enhance the performance of translation models. We investigate this approach for integrating Visual Scene Graph information into translation models, focusing on representing this information in a semantic structure rather than relying on raw image data. The performance of our approach was evaluated on the Multi30K dataset for English into German, French, and Czech translations using BLEU, chrF2, TER and COMET metrics. Our results demonstrate that utilising visual scene graph information improves translation performance. Using information on semantic structure can improve the multimodal baseline model, leading to better contextual understanding and translation accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hatami-etal-2025-leveraging">
<titleInfo>
<title>Leveraging Visual Scene Graph to Enhance Translation Quality in Multimodal Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hatami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihael</namePart>
<namePart type="family">Arcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XX: Volume 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierrette</namePart>
<namePart type="family">Bouillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Gerlach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Girletti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lise</namePart>
<namePart type="family">Volkart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Rubino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Farinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Daems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorothy</namePart>
<namePart type="family">Kenny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Geneva, Switzerland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-2-9701897-0-1</identifier>
</relatedItem>
<abstract>Despite significant advancements in Multimodal Machine Translation, understanding and effectively utilising visual scenes within multimodal models remains a complex challenge. Extracting comprehensive and relevant visual features requires extensive and detailed input data to ensure the model accurately captures objects, their attributes, and relationships within a scene. In this paper, we explore using visual scene graphs extracted from images to enhance the performance of translation models. We investigate this approach for integrating Visual Scene Graph information into translation models, focusing on representing this information in a semantic structure rather than relying on raw image data. The performance of our approach was evaluated on the Multi30K dataset for English into German, French, and Czech translations using BLEU, chrF2, TER and COMET metrics. Our results demonstrate that utilising visual scene graph information improves translation performance. Using information on semantic structure can improve the multimodal baseline model, leading to better contextual understanding and translation accuracy.</abstract>
<identifier type="citekey">hatami-etal-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.mtsummit-1.27/</url>
</location>
<part>
<date>2025-06</date>
<extent unit="page">
<start>353</start>
<end>364</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Visual Scene Graph to Enhance Translation Quality in Multimodal Machine Translation
%A Hatami, Ali
%A Arcan, Mihael
%A Buitelaar, Paul
%Y Bouillon, Pierrette
%Y Gerlach, Johanna
%Y Girletti, Sabrina
%Y Volkart, Lise
%Y Rubino, Raphael
%Y Sennrich, Rico
%Y Farinha, Ana C.
%Y Gaido, Marco
%Y Daems, Joke
%Y Kenny, Dorothy
%Y Moniz, Helena
%Y Szoc, Sara
%S Proceedings of Machine Translation Summit XX: Volume 1
%D 2025
%8 June
%I European Association for Machine Translation
%C Geneva, Switzerland
%@ 978-2-9701897-0-1
%F hatami-etal-2025-leveraging
%X Despite significant advancements in Multimodal Machine Translation, understanding and effectively utilising visual scenes within multimodal models remains a complex challenge. Extracting comprehensive and relevant visual features requires extensive and detailed input data to ensure the model accurately captures objects, their attributes, and relationships within a scene. In this paper, we explore using visual scene graphs extracted from images to enhance the performance of translation models. We investigate this approach for integrating Visual Scene Graph information into translation models, focusing on representing this information in a semantic structure rather than relying on raw image data. The performance of our approach was evaluated on the Multi30K dataset for English into German, French, and Czech translations using BLEU, chrF2, TER and COMET metrics. Our results demonstrate that utilising visual scene graph information improves translation performance. Using information on semantic structure can improve the multimodal baseline model, leading to better contextual understanding and translation accuracy.
%U https://aclanthology.org/2025.mtsummit-1.27/
%P 353-364
Markdown (Informal)
[Leveraging Visual Scene Graph to Enhance Translation Quality in Multimodal Machine Translation](https://aclanthology.org/2025.mtsummit-1.27/) (Hatami et al., MTSummit 2025)
ACL