Second Call for Participation: WMT Shared Task on Sign Language Translation (WMT-SLT)
We are excited to announce the first edition of the Shared Task on Sign Language Translation (WMT-SLT) at WMT 2022, co-located with EMNLP 2022.
NEW DEVELOPMENTS SINCE THE FIRST CALL
(1) Release of training data
The training data comprises two corpora, called FocusNews and SRF. The linguistic domain of both corpora is general news, and both contain parallel data between Swiss German Sign Language (DSGS) and German. The corpora are distributed through Zenodo.
The FocusNews data originates from a former Deaf online TV channel, FocusFive. The videos feature Deaf signers of DSGS. The SRF data are daily national news and weather forecast episodes broadcast by the Swiss National TV (Schweizerisches Radio und Fernsehen, SRF). The episodes are narrated in German and interpreted into Swiss German Sign Language (DSGS).
Please see https://www.wmt-slt.com/data for more information.
(2) Release of baseline code
We provide code to train baseline systems for DSGS to German in a public Github repository. The codebase contains scripts to preprocess data, train, translate and evaluate models.
Please see https://www.wmt-slt.com/tools for more information.
This shared task is concerned with automatic translation between signed and spoken languages. The task is novel in the sense that it requires processing visual information (such as video frames or human pose estimation) beyond the well-known paradigm of text-to-text machine translation.
We provide training data for one language pair: Swiss German Sign Language (DSGS) and German (DE).
Translation from DSGS to German is our primary translation direction: submitted systems are ranked on a leaderboard and we will provide baseline systems. Systems translating from German to DSGS are not ranked on the leaderboard while the task is running, but we still encourage participants to submit such systems.
We aim to provide human evaluation for all submitted systems, regardless of the translation direction.
We will ask participants to submit a system description paper to WMT 2022.
All deadlines are AoE (Anywhere on Earth). Dates are in line with general deadlines of WMT.
* Mathias Müller, University of Zurich
For more information, please visit our website: www.wmt-slt.com