CUNI System for the WMT18 Multimodal Translation Task

Jindřich Helcl, Jindřich Libovický, Dušan Variš

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationProceedings of the Third Conference on Machine Translation: Shared Task Papers
Place of PublicationBelgium, Brussels
PublisherAssociation for Computational Linguistics
Number of pages8
ISBN (Electronic)978-1-948087-81-0
Publication statusPublished - 31 Oct 2018
EventEMNLP 2018 Third Conference on Machine Translation (WMT18) - Brussels, Belgium
Duration: 31 Oct 20181 Nov 2018


WorkshopEMNLP 2018 Third Conference on Machine Translation (WMT18)
Abbreviated titleWMT18
Internet address


Dive into the research topics of 'CUNI System for the WMT18 Multimodal Translation Task'. Together they form a unique fingerprint.

Cite this