[CLASSLA] DIALECT-COPA shared task on dialectal commonsense reasoning

[Taja Kuzman]

CLASSLA Mailing List

Dear colleagues,

We would like to draw your attention to the DIALECT-COPA shared task, 
focused on automatic commonsense reasoning in South Slavic dialects. The 
task includes training data for four official South Slavic languages 
(Slovenian, Croatian, Serbian, Macedonian) and two out of three related 
test dialects. The test dialects are the Slovenian dialect of Cerkno 
(town of Idrija), the Croatian Chakavian dialect (town of Žminj) and the 
Serbian-Macedonian-Bulgarian Torlak dialect (town of Lebane).

A full description of the task, as well as data examples and training 
data, can be found at 
https://sites.google.com/view/vardial-2024/shared-tasks/dialect-copa.

The test data will be published on March 4, while the description of the 
system is to be submitted by March 24.

The shared task is organized as part of the 11th VarDial workshop on 
natural language processing of dialects and varieties, which will be 
co-located with the NAACL conference in Mexico this June, 
https://2024.naacl.org.

Please share this info via relevant channels!
https://www.linkedin.com/feed/update/urn:li:activity:7158815963600105472/
https://x.com/nljubesic/status/1753036926859268317

Kind regards,
Nikola Ljubešić and Taja Kuzman

CLASSLA: The Knowledge Centre for South Slavic Languages 
<https://www.clarin.si/info/k-centre/>

CLARIN.SI <http://clarin.si/>

Jožef Stefan Institute

Jamova cesta 39, Ljubljana
Slovenia

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.ijs.si/pipermail/classla/attachments/20240207/0bbc6e6f/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: EgnHzq0OLDrCZSz9.png
Type: image/png
Size: 174960 bytes
Desc: not available
URL: <https://mailman.ijs.si/pipermail/classla/attachments/20240207/0bbc6e6f/attachment-0001.png>