Projects per year
Abstract
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.
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the Third Conference on Machine Translation (WMT) : Shared Task Papers |
Editors | Ondřej 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 |
Number of pages | 9 |
Place of Publication | Stroudsburg |
Publisher | The Association for Computational Linguistics |
Publication date | 1 Nov 2018 |
Pages | 603-611 |
ISBN (Electronic) | 978-1-948087-81-0 |
DOIs | |
Publication status | Published - 1 Nov 2018 |
MoE publication type | A4 Article in conference proceedings |
Event | Conference on Machine Translation - 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium Duration: 31 Oct 2018 → 1 Nov 2018 Conference number: 3 http://www.statmt.org/wmt18/ |
Fields of Science
- 113 Computer and information sciences
- 6121 Languages
Projects
- 1 Finished
-
MeMAD: Methods for Managing Audiovisual Data: Combining Automatic Efficiency with Human Accuracy
Hirvonen, M. (Principal Investigator), Tiedemann, J. (Participant), Tiittula, L. (Participant), Sulubacak, U. (Participant), Vazquez , R. (Participant) & Koponen, M. (Participant)
European Commission / Horizon 2020
01/01/2018 → 31/03/2021
Project: Research project