A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Multimodal Transformer for Multimodal Machine Translation
2020
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
unpublished
Multimodal Machine Translation (MMT) aims to introduce information from other modality, generally static images, to improve the translation quality. Previous works propose various incorporation methods, but most of them do not consider the relative importance of multiple modalities. In MMT, equally treating text and images may encode too much irrelevant information from images which may introduce noise. In this paper, we propose the multimodal self-attention in Transformer to solve the issues
doi:10.18653/v1/2020.acl-main.400
fatcat:k3crvaqf7zavdl3htttakyqcy4