@inproceedings{nakayama-etal-2020-visually,
title = "A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking",
author = "Nakayama, Hideki and
Tamura, Akihiro and
Ninomiya, Takashi",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.518",
pages = "4204--4210",
abstract = "Visually-grounded natural language processing has become an important research direction in the past few years. However, majorities of the available cross-modal resources (e.g., image-caption datasets) are built in English and cannot be directly utilized in multilingual or non-English scenarios. In this study, we present a novel multilingual multimodal corpus by extending the Flickr30k Entities image-caption dataset with Japanese translations, which we name Flickr30k Entities JP (F30kEnt-JP). To the best of our knowledge, this is the first multilingual image-caption dataset where the captions in the two languages are parallel and have the shared annotations of many-to-many phrase-to-region linking. We believe that phrase-to-region as well as phrase-to-phrase supervision can play a vital role in fine-grained grounding of language and vision, and will promote many tasks such as multilingual image captioning and multimodal machine translation. To verify our dataset, we performed phrase localization experiments in both languages and investigated the effectiveness of our Japanese annotations as well as multilingual learning realized by our dataset.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakayama-etal-2020-visually">
<titleInfo>
<title>A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akihiro</namePart>
<namePart type="family">Tamura</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>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Visually-grounded natural language processing has become an important research direction in the past few years. However, majorities of the available cross-modal resources (e.g., image-caption datasets) are built in English and cannot be directly utilized in multilingual or non-English scenarios. In this study, we present a novel multilingual multimodal corpus by extending the Flickr30k Entities image-caption dataset with Japanese translations, which we name Flickr30k Entities JP (F30kEnt-JP). To the best of our knowledge, this is the first multilingual image-caption dataset where the captions in the two languages are parallel and have the shared annotations of many-to-many phrase-to-region linking. We believe that phrase-to-region as well as phrase-to-phrase supervision can play a vital role in fine-grained grounding of language and vision, and will promote many tasks such as multilingual image captioning and multimodal machine translation. To verify our dataset, we performed phrase localization experiments in both languages and investigated the effectiveness of our Japanese annotations as well as multilingual learning realized by our dataset.</abstract>
<identifier type="citekey">nakayama-etal-2020-visually</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.518</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4204</start>
<end>4210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking
%A Nakayama, Hideki
%A Tamura, Akihiro
%A Ninomiya, Takashi
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F nakayama-etal-2020-visually
%X Visually-grounded natural language processing has become an important research direction in the past few years. However, majorities of the available cross-modal resources (e.g., image-caption datasets) are built in English and cannot be directly utilized in multilingual or non-English scenarios. In this study, we present a novel multilingual multimodal corpus by extending the Flickr30k Entities image-caption dataset with Japanese translations, which we name Flickr30k Entities JP (F30kEnt-JP). To the best of our knowledge, this is the first multilingual image-caption dataset where the captions in the two languages are parallel and have the shared annotations of many-to-many phrase-to-region linking. We believe that phrase-to-region as well as phrase-to-phrase supervision can play a vital role in fine-grained grounding of language and vision, and will promote many tasks such as multilingual image captioning and multimodal machine translation. To verify our dataset, we performed phrase localization experiments in both languages and investigated the effectiveness of our Japanese annotations as well as multilingual learning realized by our dataset.
%U https://aclanthology.org/2020.lrec-1.518
%P 4204-4210
Markdown (Informal)
[A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking](https://aclanthology.org/2020.lrec-1.518) (Nakayama et al., LREC 2020)
ACL