@inproceedings{caglayan-etal-2021-cross,
title = "Cross-lingual Visual Pre-training for Multimodal Machine Translation",
author = "Caglayan, Ozan and
Kuyu, Menekse and
Amac, Mustafa Sercan and
Madhyastha, Pranava and
Erdem, Erkut and
Erdem, Aykut and
Specia, Lucia",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.112",
doi = "10.18653/v1/2021.eacl-main.112",
pages = "1317--1324",
abstract = "Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and visual pre-training methods. In this paper, we combine these two approaches to learn visually-grounded cross-lingual representations. Specifically, we extend the translation language modelling (Lample and Conneau, 2019) with masked region classification and perform pre-training with three-way parallel vision {\&} language corpora. We show that when fine-tuned for multimodal machine translation, these models obtain state-of-the-art performance. We also provide qualitative insights into the usefulness of the learned grounded representations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="caglayan-etal-2021-cross">
<titleInfo>
<title>Cross-lingual Visual Pre-training for Multimodal Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ozan</namePart>
<namePart type="family">Caglayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menekse</namePart>
<namePart type="family">Kuyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="given">Sercan</namePart>
<namePart type="family">Amac</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranava</namePart>
<namePart type="family">Madhyastha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erkut</namePart>
<namePart type="family">Erdem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aykut</namePart>
<namePart type="family">Erdem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and visual pre-training methods. In this paper, we combine these two approaches to learn visually-grounded cross-lingual representations. Specifically, we extend the translation language modelling (Lample and Conneau, 2019) with masked region classification and perform pre-training with three-way parallel vision & language corpora. We show that when fine-tuned for multimodal machine translation, these models obtain state-of-the-art performance. We also provide qualitative insights into the usefulness of the learned grounded representations.</abstract>
<identifier type="citekey">caglayan-etal-2021-cross</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.112</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.112</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1317</start>
<end>1324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Visual Pre-training for Multimodal Machine Translation
%A Caglayan, Ozan
%A Kuyu, Menekse
%A Amac, Mustafa Sercan
%A Madhyastha, Pranava
%A Erdem, Erkut
%A Erdem, Aykut
%A Specia, Lucia
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F caglayan-etal-2021-cross
%X Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and visual pre-training methods. In this paper, we combine these two approaches to learn visually-grounded cross-lingual representations. Specifically, we extend the translation language modelling (Lample and Conneau, 2019) with masked region classification and perform pre-training with three-way parallel vision & language corpora. We show that when fine-tuned for multimodal machine translation, these models obtain state-of-the-art performance. We also provide qualitative insights into the usefulness of the learned grounded representations.
%R 10.18653/v1/2021.eacl-main.112
%U https://aclanthology.org/2021.eacl-main.112
%U https://doi.org/10.18653/v1/2021.eacl-main.112
%P 1317-1324
Markdown (Informal)
[Cross-lingual Visual Pre-training for Multimodal Machine Translation](https://aclanthology.org/2021.eacl-main.112) (Caglayan et al., EACL 2021)
ACL
- Ozan Caglayan, Menekse Kuyu, Mustafa Sercan Amac, Pranava Madhyastha, Erkut Erdem, Aykut Erdem, and Lucia Specia. 2021. Cross-lingual Visual Pre-training for Multimodal Machine Translation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1317–1324, Online. Association for Computational Linguistics.