@inproceedings{zheng-etal-2018-ensemble,
title = "Ensemble Sequence Level Training for Multimodal {MT}: {OSU}-{B}aidu {WMT}18 Multimodal Machine Translation System Report",
author = "Zheng, Renjie and
Yang, Yilin and
Ma, Mingbo and
Huang, Liang",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6443",
doi = "10.18653/v1/W18-6443",
pages = "632--636",
abstract = "This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation. In this paper, we introduce a simple approach to incorporate image information by feeding image features to the decoder side. We also explore different sequence level training methods including scheduled sampling and reinforcement learning which lead to substantial improvements. Our systems ensemble several models using different architectures and training methods and achieve the best performance for three subtasks: En-De and En-Cs in task 1 and (En+De+Fr)-Cs task 1B.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2018-ensemble">
<titleInfo>
<title>Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renjie</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingbo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation. In this paper, we introduce a simple approach to incorporate image information by feeding image features to the decoder side. We also explore different sequence level training methods including scheduled sampling and reinforcement learning which lead to substantial improvements. Our systems ensemble several models using different architectures and training methods and achieve the best performance for three subtasks: En-De and En-Cs in task 1 and (En+De+Fr)-Cs task 1B.</abstract>
<identifier type="citekey">zheng-etal-2018-ensemble</identifier>
<identifier type="doi">10.18653/v1/W18-6443</identifier>
<location>
<url>https://aclanthology.org/W18-6443</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>632</start>
<end>636</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report
%A Zheng, Renjie
%A Yang, Yilin
%A Ma, Mingbo
%A Huang, Liang
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Belgium, Brussels
%F zheng-etal-2018-ensemble
%X This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation. In this paper, we introduce a simple approach to incorporate image information by feeding image features to the decoder side. We also explore different sequence level training methods including scheduled sampling and reinforcement learning which lead to substantial improvements. Our systems ensemble several models using different architectures and training methods and achieve the best performance for three subtasks: En-De and En-Cs in task 1 and (En+De+Fr)-Cs task 1B.
%R 10.18653/v1/W18-6443
%U https://aclanthology.org/W18-6443
%U https://doi.org/10.18653/v1/W18-6443
%P 632-636
Markdown (Informal)
[Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report](https://aclanthology.org/W18-6443) (Zheng et al., 2018)
ACL