@inproceedings{kang-etal-2023-bigvideo,
title = "{B}ig{V}ideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation",
author = "Kang, Liyan and
Huang, Luyang and
Peng, Ningxin and
Zhu, Peihao and
Sun, Zewei and
Cheng, Shanbo and
Wang, Mingxuan and
Huang, Degen and
Su, Jinsong",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.535",
doi = "10.18653/v1/2023.findings-acl.535",
pages = "8456--8473",
abstract = "We present a large-scale video subtitle translation dataset, *BigVideo*, to facilitate the study of multi-modality machine translation. Compared with the widely used *How2* and *VaTeX* datasets, *BigVideo* is more than 10 times larger, consisting of 4.5 million sentence pairs and 9,981 hours of videos. We also introduce two deliberately designed test sets to verify the necessity of visual information: *Ambiguous* with the presence of ambiguous words, and *Unambiguous* in which the text context is self-contained for translation. To better model the common semantics shared across texts and videos, we introduce a contrastive learning method in the cross-modal encoder. Extensive experiments on the *BigVideo* shows that: a) Visual information consistently improves the NMT model in terms of BLEU, BLEURT and COMET on both Ambiguous and Unambiguous test sets. b) Visual information helps disambiguation, compared to the strong text baseline on terminology-targeted scores and human evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2023-bigvideo">
<titleInfo>
<title>BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liyan</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luyang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ningxin</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peihao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zewei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanbo</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Degen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinsong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a large-scale video subtitle translation dataset, *BigVideo*, to facilitate the study of multi-modality machine translation. Compared with the widely used *How2* and *VaTeX* datasets, *BigVideo* is more than 10 times larger, consisting of 4.5 million sentence pairs and 9,981 hours of videos. We also introduce two deliberately designed test sets to verify the necessity of visual information: *Ambiguous* with the presence of ambiguous words, and *Unambiguous* in which the text context is self-contained for translation. To better model the common semantics shared across texts and videos, we introduce a contrastive learning method in the cross-modal encoder. Extensive experiments on the *BigVideo* shows that: a) Visual information consistently improves the NMT model in terms of BLEU, BLEURT and COMET on both Ambiguous and Unambiguous test sets. b) Visual information helps disambiguation, compared to the strong text baseline on terminology-targeted scores and human evaluation.</abstract>
<identifier type="citekey">kang-etal-2023-bigvideo</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.535</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.535</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>8456</start>
<end>8473</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation
%A Kang, Liyan
%A Huang, Luyang
%A Peng, Ningxin
%A Zhu, Peihao
%A Sun, Zewei
%A Cheng, Shanbo
%A Wang, Mingxuan
%A Huang, Degen
%A Su, Jinsong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kang-etal-2023-bigvideo
%X We present a large-scale video subtitle translation dataset, *BigVideo*, to facilitate the study of multi-modality machine translation. Compared with the widely used *How2* and *VaTeX* datasets, *BigVideo* is more than 10 times larger, consisting of 4.5 million sentence pairs and 9,981 hours of videos. We also introduce two deliberately designed test sets to verify the necessity of visual information: *Ambiguous* with the presence of ambiguous words, and *Unambiguous* in which the text context is self-contained for translation. To better model the common semantics shared across texts and videos, we introduce a contrastive learning method in the cross-modal encoder. Extensive experiments on the *BigVideo* shows that: a) Visual information consistently improves the NMT model in terms of BLEU, BLEURT and COMET on both Ambiguous and Unambiguous test sets. b) Visual information helps disambiguation, compared to the strong text baseline on terminology-targeted scores and human evaluation.
%R 10.18653/v1/2023.findings-acl.535
%U https://aclanthology.org/2023.findings-acl.535
%U https://doi.org/10.18653/v1/2023.findings-acl.535
%P 8456-8473
Markdown (Informal)
[BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation](https://aclanthology.org/2023.findings-acl.535) (Kang et al., Findings 2023)
ACL
- Liyan Kang, Luyang Huang, Ningxin Peng, Peihao Zhu, Zewei Sun, Shanbo Cheng, Mingxuan Wang, Degen Huang, and Jinsong Su. 2023. BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8456–8473, Toronto, Canada. Association for Computational Linguistics.