=== Apologies in advance for cross-posting ==
We need your help to preserve indigenous languages!
Due to the overwhelming success in previous workshops like LoResMT and AmericasNLP we have decided to continue to push the needle for Quechua to Spanish translations. Please participate in the first edition of the QUE-SPA speech translation shared task being held at IWSLT 2023. This low-resource task will help increase language preservation for low-resource languages. We invite advanced research and approaches of all types so bring your rule-based, statistical, neural, and more!
IMPORTANT LINKS
Dialectal and Low-resource webpage: https://iwslt.org/2022/low-resource
Data webpage: https://github.com/Llamacha/IWSLT2023_Quechua_data
Google Group: https://groups.google.com/g/iwslt-evaluation-campaign
IWSLT conference webpage: https://iwslt.org/2023/
HOW TO PARTICIPATE
Please join the IWSLT Evaluation Campaign Google Group and access the registration using the following link: https://groups.google.com/g/iwslt-evaluation-campaign
The QUE-SPA data set can be downloaded here: https://github.com/Llamacha/IWSLT2023_Quechua_data
Task submissions can be uploaded to GitHub, please email the organizers below for more details.
Evaluation scripts based on BLEU are made available via the IWSLT 2023 website.
IMPORTANT DATES
Jan 14, 2023 Release of shared task training and dev data Apr 1-15, 2023 Evaluation period Apr 24, 2023 Paper submission deadline (all papers) Apr 30, 2023 System papers update deadline May 22, 2023 Notification of acceptance May 31, 2023 Camera ready paper due July 12, 2023 Pre-recorded video due July 13-14, 2023 IWSLT conference
ORGANIZING COMMITTEE
John E. Ortega (Northeastern University) William Chen (Carnegie Mellon University) Rodolfo Zevallos (Universitat Pompeu Fabra)