@inproceedings{ye-etal-2022-noise,
title = "Noise-robust Cross-modal Interactive Learning with {T}ext2{I}mage Mask for Multi-modal Neural Machine Translation",
author = "Ye, Junjie and
Guo, Junjun and
Xiang, Yan and
Tan, Kaiwen and
Yu, Zhengtao",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.452",
pages = "5098--5108",
abstract = "Multi-modal neural machine translation (MNMT) aims to improve textual level machine translation performance in the presence of text-related images. Most of the previous works on MNMT focus on multi-modal fusion methods with full visual features. However, text and its corresponding image may not match exactly, visual noise is generally inevitable. The irrelevant image regions may mislead or distract the textual attention and cause model performance degradation. This paper proposes a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT. A text-image relation-aware attention module is constructed through the cross-modal interaction mask mechanism, and visual features are extracted based on the text-image interaction mask knowledge. Then a noise-robust multi-modal adaptive fusion approach is presented by fusion the relevant visual and textual features for machine translation. We validate our method on the Multi30K dataset. The experimental results show the superiority of our proposed model, and achieve the state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-etal-2022-noise">
<titleInfo>
<title>Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junjun</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaiwen</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengtao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal neural machine translation (MNMT) aims to improve textual level machine translation performance in the presence of text-related images. Most of the previous works on MNMT focus on multi-modal fusion methods with full visual features. However, text and its corresponding image may not match exactly, visual noise is generally inevitable. The irrelevant image regions may mislead or distract the textual attention and cause model performance degradation. This paper proposes a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT. A text-image relation-aware attention module is constructed through the cross-modal interaction mask mechanism, and visual features are extracted based on the text-image interaction mask knowledge. Then a noise-robust multi-modal adaptive fusion approach is presented by fusion the relevant visual and textual features for machine translation. We validate our method on the Multi30K dataset. The experimental results show the superiority of our proposed model, and achieve the state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks.</abstract>
<identifier type="citekey">ye-etal-2022-noise</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.452</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5098</start>
<end>5108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation
%A Ye, Junjie
%A Guo, Junjun
%A Xiang, Yan
%A Tan, Kaiwen
%A Yu, Zhengtao
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F ye-etal-2022-noise
%X Multi-modal neural machine translation (MNMT) aims to improve textual level machine translation performance in the presence of text-related images. Most of the previous works on MNMT focus on multi-modal fusion methods with full visual features. However, text and its corresponding image may not match exactly, visual noise is generally inevitable. The irrelevant image regions may mislead or distract the textual attention and cause model performance degradation. This paper proposes a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT. A text-image relation-aware attention module is constructed through the cross-modal interaction mask mechanism, and visual features are extracted based on the text-image interaction mask knowledge. Then a noise-robust multi-modal adaptive fusion approach is presented by fusion the relevant visual and textual features for machine translation. We validate our method on the Multi30K dataset. The experimental results show the superiority of our proposed model, and achieve the state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks.
%U https://aclanthology.org/2022.coling-1.452
%P 5098-5108
Markdown (Informal)
[Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation](https://aclanthology.org/2022.coling-1.452) (Ye et al., COLING 2022)
ACL