_____________________________________________________________________ HaSpeeDe 2 Hate Speech Detection shared task at EVALITA 2020
Web: http://di.unito.it/haspeede20 <http://di.unito.it/haspeede20>
EVALITA 2020, the 7th evaluation campaign of Natural Language Processing and Speech tools for Italian, 2-3 December 2020, Bologna, Italy Co-located with the 7th Italian Conference on Computational Linguistics (CLiC-it 2020).
Registration is required to obtain data and participate in the shared task. Subscribe to the google group: https://groups.google.com/d/forum/haspeede-evalita2020 <https://groups.google.com/d/forum/haspeede-evalita2020> _____________________________________________________________________
1st CALL FOR PARTICIPATION
Online hateful content, or Hate Speech (HS), is characterized by some key aspects (such as virality, or presumed anonymity) which distinguish it from offline communication and make it potentially more dangerous and hurtful. Therefore, its identification has become a crucial mission in many fields.
From an NLP perspective, much attention has been paid to the topic of HS – together with all its possible facets and related phenomena, such as offensive/abusive language, and so on – and its identification. This is shown by the proliferation, especially in the last few years, of contributions on this matter, corpora and lexica, dedicated workshops, and shared tasks within national (GermEval, HASOC, IberLEF) and international (SemEval) evaluation campaigns.
The last edition of EVALITA hosted the first HS detection in Social Media task for Italian. The high participation and the promising results encouraged us to propose a second run at EVALITA 2020. The new HaSpeeDe evaluation campaign includes 3 sub-tasks:
- HS Detection with language variety and test of time (binary task): the main task is to determine whether a message is hateful or not. We will provide a new HS dataset based on Twitter data, accompanied by two new blind test sets, one in-domain and one out-of-domain, as well as belonging to different time periods.
- Stereotype Detection (binary task): we include a task to determine whether a message contains stereotypes.
- Syntactic realization of HS and Nominal Utterances’ identification: we include a task aimed at identifying NUs in hateful messages.
The ultimate goal of this edition of HaSpeeDe is thus to take a step further in the state of the art of HS detection for Italian also exploring other side phenomena, the extent to which they can be distinguished from HS, and finally whether and how much automatic systems are able to draw such distinction.
6th April 2020: registration opens (http://www.evalita.it/2020/taskregistration <http://www.evalita.it/2020/taskregistration>) 29th May 2020: training data available to participants 4th September 2020: registration closes 4th-11th Sept. 2020: evaluation window and collection of participants' results 6th November 2020: technical reports due to organizers - TENTATIVE 2nd-3rd December 2020: final workshop
Cristina Bosco, Simona Frenda, Viviana Patti, Manuela Sanguinetti (main contact), Dip. di Informatica, University of Turin, Italy Tommaso Caselli, Center for Language and Cognition, University of Groningen, The Netherlands Gloria Comandini, Dip. di Lettere e Filosofia, University of Trento, Italy Elisa Di Nuovo, Dip. Lingue e Letterature Straniere e Culture Moderne, University of Turin, Italy Irene Russo, ILC "A. Zampolli" - CNR, Pisa, Italy Marco Stranisci, Acmos, Italy
If you have any enquiries/comments, contact us via: haspeede-evalita2020 at gouglegroups.com <mailto:haspeede-evalita2020 at gouglegroups.com>
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 5007 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20200427/e15a57d4/attachment.txt>