@inproceedings{helcl-etal-2018-cuni,
title = "{CUNI} System for the {WMT}18 Multimodal Translation Task",
author = "Helcl, Jind{\v{r}}ich and
Libovick{\'y}, Jind{\v{r}}ich and
Vari{\v{s}}, Du{\v{s}}an",
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/W18-6441",
doi = "10.18653/v1/W18-6441",
pages = "616--623",
abstract = "We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a self-attentive network instead of a recurrent neural network. We evaluate two methods of incorporating the visual features in the model: first, we include the image representation as another input to the network; second, we train the model to predict the visual features and use it as an auxiliary objective. For our submission, we acquired both textual and multimodal additional data. Both of the proposed methods yield significant improvements over recurrent networks and self-attentive textual baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="helcl-etal-2018-cuni">
<titleInfo>
<title>CUNI System for the WMT18 Multimodal Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jindřich</namePart>
<namePart type="family">Helcl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jindřich</namePart>
<namePart type="family">Libovický</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dušan</namePart>
<namePart type="family">Variš</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>We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a self-attentive network instead of a recurrent neural network. We evaluate two methods of incorporating the visual features in the model: first, we include the image representation as another input to the network; second, we train the model to predict the visual features and use it as an auxiliary objective. For our submission, we acquired both textual and multimodal additional data. Both of the proposed methods yield significant improvements over recurrent networks and self-attentive textual baselines.</abstract>
<identifier type="citekey">helcl-etal-2018-cuni</identifier>
<identifier type="doi">10.18653/v1/W18-6441</identifier>
<location>
<url>https://aclanthology.org/W18-6441</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>616</start>
<end>623</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUNI System for the WMT18 Multimodal Translation Task
%A Helcl, Jindřich
%A Libovický, Jindřich
%A Variš, Dušan
%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 helcl-etal-2018-cuni
%X We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a self-attentive network instead of a recurrent neural network. We evaluate two methods of incorporating the visual features in the model: first, we include the image representation as another input to the network; second, we train the model to predict the visual features and use it as an auxiliary objective. For our submission, we acquired both textual and multimodal additional data. Both of the proposed methods yield significant improvements over recurrent networks and self-attentive textual baselines.
%R 10.18653/v1/W18-6441
%U https://aclanthology.org/W18-6441
%U https://doi.org/10.18653/v1/W18-6441
%P 616-623
Markdown (Informal)
[CUNI System for the WMT18 Multimodal Translation Task](https://aclanthology.org/W18-6441) (Helcl et al., 2018)
ACL
- Jindřich Helcl, Jindřich Libovický, and Dušan Variš. 2018. CUNI System for the WMT18 Multimodal Translation Task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 616–623, Belgium, Brussels. Association for Computational Linguistics.