The MeMAD Submission to the WMT18 Multimodal Translation Task
Permalink
Citation
Grönroos , S-A , Huet , B , Kurimo , M , Laaksonen , J , Merialdo , B , Pham , P , Sjöberg , M , Sulubacak , U , Tiedemann , J , Troncy , R & Vázquez Carrillo , J R 2018 , The MeMAD Submission to the WMT18 Multimodal Translation Task . in O Bojar , R Chatterjee , C Federmann , M Fishel , Y Graham , B Haddow , M Huck , A J Yepes , P Koehn , C Monz , M Negri , A Névéol , M Neves , M Post , L Specia , M Turchi & K Verspoor (eds) , Proceedings of the Third Conference on Machine Translation (WMT) : Shared Task Papers . The Association for Computational Linguistics , Stroudsburg , pp. 603-611 , Conference on Machine Translation , Brussels , Belgium , 31/10/2018 . https://doi.org/10.18653/v1/W18-6439
| Title: | The MeMAD Submission to the WMT18 Multimodal Translation Task |
| Author: | Grönroos, Stig-Arne; Huet, Benoit; Kurimo, Mikko; Laaksonen, Jorma; Merialdo, Bernard; Pham, Phu; Sjöberg, Mats; Sulubacak, Umut; Tiedemann, Jörg; Troncy, Raphaël; Vázquez Carrillo, Juan Raúl |
| Other contributor: |
Bojar, Ondřej
Chatterjee, Rajen Federmann, Christian Fishel, Mark Graham, Yvette Haddow, Barry Huck, Matthias Yepes, Antonio Jimeno Koehn, Philipp Monz, Christof Negri, Matteo Névéol, Aurélie Neves, Mariana Post, Matt Specia, Lucia Turchi, Marco Verspoor, Karin |
| Contributor organization: | Department of Digital Humanities Language Technology |
| Publisher: | The Association for Computational Linguistics |
| Date: | 2018-11-01 |
| Language: | eng |
| Number of pages: | 9 |
| Belongs to series: | Proceedings of the Third Conference on Machine Translation (WMT) |
| ISBN: | 978-1-948087-81-0 |
| DOI: | https://doi.org/10.18653/v1/W18-6439 |
| URI: | http://hdl.handle.net/10138/263699 |
| 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. |
| Subject: |
113 Computer and information sciences
6121 Languages |
| Peer reviewed: | Yes |
| Rights: | unspecified |
| Usage restriction: | openAccess |
| Self-archived version: | publishedVersion |
| Funder: | European Commission / Horizon 2020 |
| Grant number: |
Files in this item
Total number of downloads: Loading...
| Files | Size | Format | View |
|---|---|---|---|
| wmt18_SysDescription_HYAalto_1_multimodalNMT_U.pdf | 1.907Mb |
View/ |
This item appears in the following Collection(s)
-
Articles from TUHAT system
[53348]