Video-guided machine translation as one of multimodal neural machine translation tasks targeting on generating high-quality text translation by tangibly engaging both video and text. In this work, we presented our video-guided machine translation system in approaching the Video-guided Machine Translation Challenge 2020. This system employs keyframe-based video feature extractions along with the video feature positional encoding. In the evaluation phase, our system scored 36.60 corpus-level BLEU-4 and achieved the 1st place on the Video-guided Machine Translation Challenge 2020.
@article{arxiv.2006.12799,
title = {Keyframe Segmentation and Positional Encoding for Video-guided Machine Translation Challenge 2020},
author = {Tosho Hirasawa and Zhishen Yang and Mamoru Komachi and Naoaki Okazaki},
journal= {arXiv preprint arXiv:2006.12799},
year = {2020}
}
Comments
4 pages; First Workshop on Advances in Language and Vision Research (ALVR 2020)