The MeMAD Submission to the WMT18 Multimodal Translation Task

08/31/2018
by   Stig-Arne Grönroos, et al.
0

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 English-to-German and fifth for 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.

READ FULL TEXT
research
09/01/2018

LIUM-CVC Submissions for WMT18 Multimodal Translation Task

This paper describes the multimodal Neural Machine Translation systems d...
research
08/17/2023

Factuality Detection using Machine Translation – a Use Case for German Clinical Text

Factuality can play an important role when automatically processing clin...
research
05/30/2018

Marian: Cost-effective High-Quality Neural Machine Translation in C++

This paper describes the submissions of the "Marian" team to the WNMT 20...
research
05/24/2019

DebiasingWord Embeddings Improves Multimodal Machine Translation

In recent years, pretrained word embeddings have proved useful for multi...
research
08/16/2023

Fast Training of NMT Model with Data Sorting

The Transformer model has revolutionized Natural Language Processing tas...
research
07/04/2017

Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation

In Multimodal Neural Machine Translation (MNMT), a neural model generate...
research
01/23/2017

Incorporating Global Visual Features into Attention-Based Neural Machine Translation

We introduce multi-modal, attention-based neural machine translation (NM...

Please sign up or login with your details

Forgot password? Click here to reset