papers AI Learner
The Github is limit! Click to go to the new site.

UMONS Submission for WMT18 Multimodal Translation Task

2018-10-15
Jean-Benoit Delbrouck, Stéphane Dupont

Abstract

This paper describes the UMONS solution for the Multimodal Machine Translation Task presented at the third conference on machine translation (WMT18). We explore a novel architecture, called deepGRU, based on recent findings in the related task of Neural Image Captioning (NIC). The models presented in the following sections lead to the best METEOR translation score for both constrained (English, image) -> German and (English, image) -> French sub-tasks.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1810.06233

PDF

https://arxiv.org/pdf/1810.06233


Similar Posts

Comments