@inproceedings{manabe-etal-2026-domain,
title = "Domain Adaptation of Image Encoder for Multimodal Manga Translation",
author = "Manabe, Kota and
Kajiwara, Tomoyuki and
Ninomiya, Takashi and
Goto, Isao and
Ishiwatari, Shonosuke and
Noji, Hiroshi",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.3/",
pages = "17--26",
ISBN = "979-8-89176-383-8",
abstract = "The objective of this paper is to enhance machine translation for manga (Japanese comics) by developing and employing an image encoder that is capable of more accurately comprehending its visual context. Conventional manga machine translation systems have faced the challenge of lacking sufficient manga comprehension capabilities when utilizing image information. To address this issue, we propose a domain-adapted image encoder training method for manga. The proposed method involves training encoders to acquire visual features that consider the structural and sequential characteristics of the manga. This approach draws upon a technique that has proven to be highly effective in training language models. The image encoders trained by the proposed methods are used as visual processors in a multimodal machine translation model, and they are evaluated in a Japanese-English translation task. The experimental results demonstrate that the proposed method enhances the performance metrics for translation evaluation, such as BLEU and xCOMET, in comparison to the conventional method."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manabe-etal-2026-domain">
<titleInfo>
<title>Domain Adaptation of Image Encoder for Multimodal Manga Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kota</namePart>
<namePart type="family">Manabe</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">Takashi</namePart>
<namePart type="family">Ninomiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shonosuke</namePart>
<namePart type="family">Ishiwatari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroshi</namePart>
<namePart type="family">Noji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>The objective of this paper is to enhance machine translation for manga (Japanese comics) by developing and employing an image encoder that is capable of more accurately comprehending its visual context. Conventional manga machine translation systems have faced the challenge of lacking sufficient manga comprehension capabilities when utilizing image information. To address this issue, we propose a domain-adapted image encoder training method for manga. The proposed method involves training encoders to acquire visual features that consider the structural and sequential characteristics of the manga. This approach draws upon a technique that has proven to be highly effective in training language models. The image encoders trained by the proposed methods are used as visual processors in a multimodal machine translation model, and they are evaluated in a Japanese-English translation task. The experimental results demonstrate that the proposed method enhances the performance metrics for translation evaluation, such as BLEU and xCOMET, in comparison to the conventional method.</abstract>
<identifier type="citekey">manabe-etal-2026-domain</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.3/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>17</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain Adaptation of Image Encoder for Multimodal Manga Translation
%A Manabe, Kota
%A Kajiwara, Tomoyuki
%A Ninomiya, Takashi
%A Goto, Isao
%A Ishiwatari, Shonosuke
%A Noji, Hiroshi
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F manabe-etal-2026-domain
%X The objective of this paper is to enhance machine translation for manga (Japanese comics) by developing and employing an image encoder that is capable of more accurately comprehending its visual context. Conventional manga machine translation systems have faced the challenge of lacking sufficient manga comprehension capabilities when utilizing image information. To address this issue, we propose a domain-adapted image encoder training method for manga. The proposed method involves training encoders to acquire visual features that consider the structural and sequential characteristics of the manga. This approach draws upon a technique that has proven to be highly effective in training language models. The image encoders trained by the proposed methods are used as visual processors in a multimodal machine translation model, and they are evaluated in a Japanese-English translation task. The experimental results demonstrate that the proposed method enhances the performance metrics for translation evaluation, such as BLEU and xCOMET, in comparison to the conventional method.
%U https://aclanthology.org/2026.eacl-srw.3/
%P 17-26
Markdown (Informal)
[Domain Adaptation of Image Encoder for Multimodal Manga Translation](https://aclanthology.org/2026.eacl-srw.3/) (Manabe et al., EACL 2026)
ACL
- Kota Manabe, Tomoyuki Kajiwara, Takashi Ninomiya, Isao Goto, Shonosuke Ishiwatari, and Hiroshi Noji. 2026. Domain Adaptation of Image Encoder for Multimodal Manga Translation. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 17–26, Rabat, Morocco. Association for Computational Linguistics.