@inproceedings{hatami-etal-2024-english,
title = "{E}nglish-to-Low-Resource Translation: A Multimodal Approach for {H}indi, {M}alayalam, {B}engali, and {H}ausa",
author = "Hatami, Ali and
Banerjee, Shubhanker and
Arcan, Mihael and
Chakravarthi, Bharathi and
Buitelaar, Paul and
Mccrae, John",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Ninth Conference on Machine Translation",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wmt-1.76",
pages = "815--822",
abstract = "Multimodal machine translation leverages multiple data modalities to enhance translation quality, particularly for low-resourced languages. This paper uses a Multimodal model that integrates visual information with textual data to improve translation accuracy from English to Hindi, Malayalam, Bengali, and Hausa. This approach employs a gated fusion mechanism to effectively combine the outputs of textual and visual encoders, enabling more nuanced translations that consider both language and contextual visual cues. The performance of the multimodal model was evaluated against the text-only machine translation model based on BLEU, ChrF2 and TER. Experimental results demonstrate that the multimodal approach consistently outperforms the text-only baseline, highlighting the potential of integrating visual information in low-resourced language translation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hatami-etal-2024-english">
<titleInfo>
<title>English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa</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">Shubhanker</namePart>
<namePart type="family">Banerjee</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">Bharathi</namePart>
<namePart type="family">Chakravarthi</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>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Mccrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal machine translation leverages multiple data modalities to enhance translation quality, particularly for low-resourced languages. This paper uses a Multimodal model that integrates visual information with textual data to improve translation accuracy from English to Hindi, Malayalam, Bengali, and Hausa. This approach employs a gated fusion mechanism to effectively combine the outputs of textual and visual encoders, enabling more nuanced translations that consider both language and contextual visual cues. The performance of the multimodal model was evaluated against the text-only machine translation model based on BLEU, ChrF2 and TER. Experimental results demonstrate that the multimodal approach consistently outperforms the text-only baseline, highlighting the potential of integrating visual information in low-resourced language translation tasks.</abstract>
<identifier type="citekey">hatami-etal-2024-english</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.76</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>815</start>
<end>822</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa
%A Hatami, Ali
%A Banerjee, Shubhanker
%A Arcan, Mihael
%A Chakravarthi, Bharathi
%A Buitelaar, Paul
%A Mccrae, John
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F hatami-etal-2024-english
%X Multimodal machine translation leverages multiple data modalities to enhance translation quality, particularly for low-resourced languages. This paper uses a Multimodal model that integrates visual information with textual data to improve translation accuracy from English to Hindi, Malayalam, Bengali, and Hausa. This approach employs a gated fusion mechanism to effectively combine the outputs of textual and visual encoders, enabling more nuanced translations that consider both language and contextual visual cues. The performance of the multimodal model was evaluated against the text-only machine translation model based on BLEU, ChrF2 and TER. Experimental results demonstrate that the multimodal approach consistently outperforms the text-only baseline, highlighting the potential of integrating visual information in low-resourced language translation tasks.
%U https://aclanthology.org/2024.wmt-1.76
%P 815-822
Markdown (Informal)
[English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa](https://aclanthology.org/2024.wmt-1.76) (Hatami et al., WMT 2024)
ACL
- Ali Hatami, Shubhanker Banerjee, Mihael Arcan, Bharathi Chakravarthi, Paul Buitelaar, and John Mccrae. 2024. English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa. In Proceedings of the Ninth Conference on Machine Translation, pages 815–822, Miami, Florida, USA. Association for Computational Linguistics.