@inproceedings{teramen-etal-2024-english,
title = "{E}nglish-to-{J}apanese Multimodal Machine Translation Based on Image-Text Matching of Lecture Videos",
author = "Teramen, Ayu and
Ohtsuka, Takumi and
Kondo, Risa and
Kajiwara, Tomoyuki and
Ninomiya, Takashi",
editor = "Gu, Jing and
Fu, Tsu-Jui (Ray) and
Hudson, Drew and
Celikyilmaz, Asli and
Wang, William",
booktitle = "Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.alvr-1.7",
doi = "10.18653/v1/2024.alvr-1.7",
pages = "86--91",
abstract = "We work on a multimodal machine translation of the audio contained in English lecture videos to generate Japanese subtitles. Image-guided multimodal machine translation is promising for error correction in speech recognition and for text disambiguation. In our situation, lecture videos provide a variety of images. Images of presentation materials can complement information not available from audio and may help improve translation quality. However, images of speakers or audiences would not directly affect the translation quality. We construct a multimodal parallel corpus with automatic speech recognition text and multiple images for a transcribed parallel corpus of lecture videos, and propose a method to select the most relevant ones from the multiple images with the speech text for improving the performance of image-guided multimodal machine translation. Experimental results on translating automatic speech recognition or transcribed English text into Japanese show the effectiveness of our method to select a relevant image.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="teramen-etal-2024-english">
<titleInfo>
<title>English-to-Japanese Multimodal Machine Translation Based on Image-Text Matching of Lecture Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Teramen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takumi</namePart>
<namePart type="family">Ohtsuka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Risa</namePart>
<namePart type="family">Kondo</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>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsu-Jui</namePart>
<namePart type="given">(Ray)</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drew</namePart>
<namePart type="family">Hudson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We work on a multimodal machine translation of the audio contained in English lecture videos to generate Japanese subtitles. Image-guided multimodal machine translation is promising for error correction in speech recognition and for text disambiguation. In our situation, lecture videos provide a variety of images. Images of presentation materials can complement information not available from audio and may help improve translation quality. However, images of speakers or audiences would not directly affect the translation quality. We construct a multimodal parallel corpus with automatic speech recognition text and multiple images for a transcribed parallel corpus of lecture videos, and propose a method to select the most relevant ones from the multiple images with the speech text for improving the performance of image-guided multimodal machine translation. Experimental results on translating automatic speech recognition or transcribed English text into Japanese show the effectiveness of our method to select a relevant image.</abstract>
<identifier type="citekey">teramen-etal-2024-english</identifier>
<identifier type="doi">10.18653/v1/2024.alvr-1.7</identifier>
<location>
<url>https://aclanthology.org/2024.alvr-1.7</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>86</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T English-to-Japanese Multimodal Machine Translation Based on Image-Text Matching of Lecture Videos
%A Teramen, Ayu
%A Ohtsuka, Takumi
%A Kondo, Risa
%A Kajiwara, Tomoyuki
%A Ninomiya, Takashi
%Y Gu, Jing
%Y Fu, Tsu-Jui (Ray)
%Y Hudson, Drew
%Y Celikyilmaz, Asli
%Y Wang, William
%S Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F teramen-etal-2024-english
%X We work on a multimodal machine translation of the audio contained in English lecture videos to generate Japanese subtitles. Image-guided multimodal machine translation is promising for error correction in speech recognition and for text disambiguation. In our situation, lecture videos provide a variety of images. Images of presentation materials can complement information not available from audio and may help improve translation quality. However, images of speakers or audiences would not directly affect the translation quality. We construct a multimodal parallel corpus with automatic speech recognition text and multiple images for a transcribed parallel corpus of lecture videos, and propose a method to select the most relevant ones from the multiple images with the speech text for improving the performance of image-guided multimodal machine translation. Experimental results on translating automatic speech recognition or transcribed English text into Japanese show the effectiveness of our method to select a relevant image.
%R 10.18653/v1/2024.alvr-1.7
%U https://aclanthology.org/2024.alvr-1.7
%U https://doi.org/10.18653/v1/2024.alvr-1.7
%P 86-91
Markdown (Informal)
[English-to-Japanese Multimodal Machine Translation Based on Image-Text Matching of Lecture Videos](https://aclanthology.org/2024.alvr-1.7) (Teramen et al., ALVR-WS 2024)
ACL