@inproceedings{zhao-etal-2020-double,
title = "Double Attention-based Multimodal Neural Machine Translation with Semantic Image Regions",
author = "Zhao, Yuting and
Komachi, Mamoru and
Kajiwara, Tomoyuki and
Chu, Chenhui",
editor = "Martins, Andr{\'e} and
Moniz, Helena and
Fumega, Sara and
Martins, Bruno and
Batista, Fernando and
Coheur, Luisa and
Parra, Carla and
Trancoso, Isabel and
Turchi, Marco and
Bisazza, Arianna and
Moorkens, Joss and
Guerberof, Ana and
Nurminen, Mary and
Marg, Lena and
Forcada, Mikel L.",
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.12",
pages = "105--114",
abstract = "Existing studies on multimodal neural machine translation (MNMT) have mainly focused on the effect of combining visual and textual modalities to improve translations. However, it has been suggested that the visual modality is only marginally beneficial. Conventional visual attention mechanisms have been used to select the visual features from equally-sized grids generated by convolutional neural networks (CNNs), and may have had modest effects on aligning the visual concepts associated with textual objects, because the grid visual features do not capture semantic information. In contrast, we propose the application of semantic image regions for MNMT by integrating visual and textual features using two individual attention mechanisms (double attention). We conducted experiments on the Multi30k dataset and achieved an improvement of 0.5 and 0.9 BLEU points for English-German and English-French translation tasks, compared with the MNMT with grid visual features. We also demonstrated concrete improvements on translation performance benefited from semantic image regions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2020-double">
<titleInfo>
<title>Double Attention-based Multimodal Neural Machine Translation with Semantic Image Regions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuting</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</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">Fumega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Batista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Parra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joss</namePart>
<namePart type="family">Moorkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Guerberof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Marg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Lisboa, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing studies on multimodal neural machine translation (MNMT) have mainly focused on the effect of combining visual and textual modalities to improve translations. However, it has been suggested that the visual modality is only marginally beneficial. Conventional visual attention mechanisms have been used to select the visual features from equally-sized grids generated by convolutional neural networks (CNNs), and may have had modest effects on aligning the visual concepts associated with textual objects, because the grid visual features do not capture semantic information. In contrast, we propose the application of semantic image regions for MNMT by integrating visual and textual features using two individual attention mechanisms (double attention). We conducted experiments on the Multi30k dataset and achieved an improvement of 0.5 and 0.9 BLEU points for English-German and English-French translation tasks, compared with the MNMT with grid visual features. We also demonstrated concrete improvements on translation performance benefited from semantic image regions.</abstract>
<identifier type="citekey">zhao-etal-2020-double</identifier>
<location>
<url>https://aclanthology.org/2020.eamt-1.12</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>105</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Double Attention-based Multimodal Neural Machine Translation with Semantic Image Regions
%A Zhao, Yuting
%A Komachi, Mamoru
%A Kajiwara, Tomoyuki
%A Chu, Chenhui
%Y Martins, André
%Y Moniz, Helena
%Y Fumega, Sara
%Y Martins, Bruno
%Y Batista, Fernando
%Y Coheur, Luisa
%Y Parra, Carla
%Y Trancoso, Isabel
%Y Turchi, Marco
%Y Bisazza, Arianna
%Y Moorkens, Joss
%Y Guerberof, Ana
%Y Nurminen, Mary
%Y Marg, Lena
%Y Forcada, Mikel L.
%S Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
%D 2020
%8 November
%I European Association for Machine Translation
%C Lisboa, Portugal
%F zhao-etal-2020-double
%X Existing studies on multimodal neural machine translation (MNMT) have mainly focused on the effect of combining visual and textual modalities to improve translations. However, it has been suggested that the visual modality is only marginally beneficial. Conventional visual attention mechanisms have been used to select the visual features from equally-sized grids generated by convolutional neural networks (CNNs), and may have had modest effects on aligning the visual concepts associated with textual objects, because the grid visual features do not capture semantic information. In contrast, we propose the application of semantic image regions for MNMT by integrating visual and textual features using two individual attention mechanisms (double attention). We conducted experiments on the Multi30k dataset and achieved an improvement of 0.5 and 0.9 BLEU points for English-German and English-French translation tasks, compared with the MNMT with grid visual features. We also demonstrated concrete improvements on translation performance benefited from semantic image regions.
%U https://aclanthology.org/2020.eamt-1.12
%P 105-114
Markdown (Informal)
[Double Attention-based Multimodal Neural Machine Translation with Semantic Image Regions](https://aclanthology.org/2020.eamt-1.12) (Zhao et al., EAMT 2020)
ACL