The MeMAD Submission to the WMT18 Multimodal Translation Task

Stig-Arne Grönroos, Benoit Huet, Mikko Kurimo, Jorma Laaksonen, Bernard Merialdo, Phu Pham, Mats Sjöberg, Umut Sulubacak, Jörg Tiedemann, Raphaël Troncy, Juan Raúl Vázquez Carrillo

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

This paper describes the MeMAD project entry to the WMT Multimodal Machine
Translation Shared Task.

We propose adapting the Transformer neural machine translation (NMT) architecture to a multi-modal setting. In this paper, we also describe the preliminary experiments with text-only translation systems leading us up to this choice.

We have the top scoring system for both English-to-German and English-to-French, according to the automatic metrics for flickr18.

Our experiments show that the effect of the visual features in our system is small. Our largest gains come from the quality of the underlying text-only NMT system. We find that appropriate use of additional data is effective.
Originalspråkengelska
Titel på värdpublikationProceedings of the Third Conference on Machine Translation (WMT) : Shared Task Papers
RedaktörerOndřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
Antal sidor9
UtgivningsortStroudsburg
FörlagThe Association for Computational Linguistics
Utgivningsdatum1 nov. 2018
Sidor603-611
ISBN (elektroniskt)978-1-948087-81-0
DOI
StatusPublicerad - 1 nov. 2018
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangConference on Machine Translation - 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgien
Varaktighet: 31 okt. 20181 nov. 2018
Konferensnummer: 3
http://www.statmt.org/wmt18/

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap
  • 6121 Språkvetenskaper

Citera det här