Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation

Madhyastha, P., Wang, J.K. orcid.org/0000-0003-0048-3893 and Specia, L. (2017) Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation. In: Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers. Second Conference on Machine Translation (WMT17), 07 Sep 2018 - 08 Sep 2017, Copenhagen, Denmark. Association for Computational Linguistics , pp. 470-476.

Abstract

This paper describes the University of Sheffield’s submission to the WMT17 Multimodal Machine Translation shared task. We participated in Task 1 to develop an MT system to translate an image description from English to German and French, given its corresponding image. Our proposed systems are based on the state-of-the-art Neural Machine Translation approach. We investigate the effect of replacing the commonly-used image embeddings with an estimated posterior probability prediction for 1,000 object categories in the images.

Metadata

Authors/Creators:

Madhyastha, P.
Wang, J.K. https://orcid.org/0000-0003-0048-3893
Specia, L.

© 2017 Association for Computational Linguistics. This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Dates: