We are happy to announce that the 2019 Surface Realization Shared Task (SR'19) is now open!
For this second edition of the challenge, the general objective is again to produce a well-formed sentence out of the given input structures derived from the UD dataset. This year, there are 11 different languages, including 5 new ones: Chinese, Hindi, Indonesian, Japanese and Korean. SR'19 is organized as part of the Multilingual Surface Realization workshop, which will be collocated with EMNLP in Hong Kong in November. To find out about the task, the datasets, and much more, please visit our page!
---WEBPAGE---
http://taln.upf.edu/pages/msr2019-ws/SRST.html
---IMPORTANT DATES---
April 5, 2019: Registration for the task open
April 5, 2019: Training and development sets released, evaluation scripts released
August 3, 2019: Test sets released
August 19, 2019: System outputs collected
August 30, 2019: Automatic evaluation due
September 9, 2019: System descriptions papers due
September 21, 2019: Human evaluation due
September 21, 2019: Notification of acceptance
September 30, 2019: Camera-ready papers due
November 3-4, 2019: Presentation of results and systems @EMLNP
---REGISTRATION---
In order to register for the task, please send an email to msr.organizers [at] gmail.com with your name and affiliation, and you will receive a link for downloading the data. There is no obligation to submit results, and we do not disclose the identity of the registered teams.
---ORGANIZERS---
Anya Belz, University of Brighton, Brighton, UK
Bernd Bohnet, Google Research, London, UK
Yvette Graham, ADAPT Center, DCU, Dublin, Ireland
Simon Mille, Pompeu Fabra University, Barcelona, Spain
Leo Wanner, Pompeu Fabra University and ICREA, Barcelona, Spain