The MeMAD submission to the WMT18 multimodal translation task

No Thumbnail Available
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
Date
2018
Major/Subject
Mcode
Degree programme
Language
en
Pages
9
609-617
Series
Proceedings of the Third Conference on Machine Translation (WMT), Volume 2: Shared Task Papers, Volume 2
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.
Description
| openaire: EC/H2020/780069/EU//MeMAD
Keywords
Other note
Citation
Grönroos, S-A, Huet, B, Kurimo, M, Laaksonen, J, Merialdo, B, Pham, P, Sjöberg, M, Sulubacak, U, Tiedemann, J, Troncy, R & Vázquez, R 2018, The MeMAD submission to the WMT18 multimodal translation task . in Proceedings of the Third Conference on Machine Translation (WMT), Volume 2: Shared Task Papers . vol. 2, Association for Computational Linguistics, pp. 609-617, Conference on Machine Translation, Brussels, Belgium, 31/10/2018 . https://doi.org/10.18653/v1/W18-6439