Publication
Spatio-temporal Sign Language Representation and Translation
Yasser Hamidullah; Josef van Genabith; Cristina España-Bonet
In: Proceedings of the Seventh Conference on Machine Translation. Conference on Machine Translation (WMT-2022), Abu Dhabi, Pages 977-982, Association for Computational Linguistics, 12/2022.
Abstract
This paper describes the DFKI-MLT submission to the WMT-SLT 2022 sign language translation (SLT) task from Swiss German Sign Language (video) into German (text). State-of-the-art techniques for SLT use a generic seq2seq architecture with customized input embeddings. Instead of word embeddings as used in textual machine translation, SLT systems use features extracted from video frames. Standard approaches often do not benefit from temporal features. In our participation, we present a system that learns spatio-temporal feature representations and translation in a single model, resulting in a real end-to-end architecture expected to better generalize to new data sets. Our best system achieved $5pm1$ BLEU points on the development set, but the performance on the test dropped to 0.11+-0.06 BLEU points.