@inproceedings{mohammadshahi-etal-2019-aligning-multilingual,
title = "Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task",
author = "Mohammadshahi, Alireza and
Lebret, R{\'e}mi and
Aberer, Karl",
editor = "Thorne, James and
Vlachos, Andreas and
Cocarascu, Oana and
Christodoulopoulos, Christos and
Mittal, Arpit",
booktitle = "Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6605",
doi = "10.18653/v1/D19-6605",
pages = "27--33",
abstract = "In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k with German and English captions and Microsoft-COCO with English and Japanese captions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammadshahi-etal-2019-aligning-multilingual">
<titleInfo>
<title>Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alireza</namePart>
<namePart type="family">Mohammadshahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Lebret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="family">Aberer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)</title>
</titleInfo>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Thorne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k with German and English captions and Microsoft-COCO with English and Japanese captions.</abstract>
<identifier type="citekey">mohammadshahi-etal-2019-aligning-multilingual</identifier>
<identifier type="doi">10.18653/v1/D19-6605</identifier>
<location>
<url>https://aclanthology.org/D19-6605</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>27</start>
<end>33</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task
%A Mohammadshahi, Alireza
%A Lebret, Rémi
%A Aberer, Karl
%Y Thorne, James
%Y Vlachos, Andreas
%Y Cocarascu, Oana
%Y Christodoulopoulos, Christos
%Y Mittal, Arpit
%S Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F mohammadshahi-etal-2019-aligning-multilingual
%X In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k with German and English captions and Microsoft-COCO with English and Japanese captions.
%R 10.18653/v1/D19-6605
%U https://aclanthology.org/D19-6605
%U https://doi.org/10.18653/v1/D19-6605
%P 27-33
Markdown (Informal)
[Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task](https://aclanthology.org/D19-6605) (Mohammadshahi et al., 2019)
ACL