Second WMT shared task on sign language translation



01/08/2023               Participation instructions are now live. 

28/07/2023               Our test set can now be downloaded

26/06/2023 We shifted our remaining deadlines by two weeks, to
give participants more time. See updated schedule.

22/06/2023 Our training data SRF can now be downloaded

06/06/2023               Our training data Signsuisse can now be downloaded

16/05/2023 Delayed release of training data for one more week

02/05/2023 Schedule is updated due to delays in data preparation. 

22/03/2023 2023 Website is up. Last year's site can be found here.  

Shared task in a nutshell

We are excited to announce the second edition of the Shared Task on Sign Language Translation (WMT-SLT 23) at WMT 2023, co-located with EMNLP 2023.

This shared task is concerned with automatic translation between signed and spoken languages. The task requires processing visual information (such as video frames or human pose estimation) beyond the well-known paradigm of text-to-text machine translation. 

This year the shared task features two tracks: translation from a signed language to a spoken language (signed-to-spoken track) and vice versa (spoken-to-signed track). We cover the following translation directions:



We provide training data and baseline systems for all translation directions above.

Submissions to the signed-to-spoken track will be ranked on a leaderboard. Submissions to the spoken-to-signed track 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 2023.