31.1391, FYI: Call for Participation: Automatic Misogyny Identification at Evalita 2020

[The LINGUIST List]

LINGUIST List: Vol-31-1391. Sat Apr 18 2020. ISSN: 1069 - 4875.

Subject: 31.1391, FYI:  Call for Participation: Automatic Misogyny Identification at Evalita 2020

Moderator: Malgorzata E. Cavar (linguist at linguistlist.org)
Student Moderator: Jeremy Coburn
Managing Editor: Becca Morris
Team: Helen Aristar-Dry, Everett Green, Sarah Robinson, Lauren Perkins, Nils Hjortnaes, Yiwen Zhang, Joshua Sims
Jobs: jobs at linguistlist.org | Conferences: callconf at linguistlist.org | Pubs: pubs at linguistlist.org

Homepage: http://linguistlist.org

Please support the LL editors and operation with a donation at:
           https://funddrive.linguistlist.org/donate/

Editor for this issue: Sarah Robinson <srobinson at linguistlist.org>
================================================================


Date: Sat, 18 Apr 2020 13:51:11
From: Elisabetta Fersini [elisabetta.fersini at unimib.it]
Subject: Call for Participation: Automatic Misogyny Identification at Evalita 2020

 
First Call for Participation:

EVALITA 2020:

Task: Automatic Misogyny Identification (AMI)

Webpage: https://amievalita2020.github.io/

2-3 December 2020, Bologna, Italy

We are launching the second edition of the AMI shared task at Evalita 2020.
AMI is aimed at automatically and fairly identifying misogynous content on
Twitter in Italian language. Misogyny, as a form of hate against women, is
typically presented in different forms such as threats of violence and sexual
objectification. While misogyny has been historically analysed from
psychological and sociological points of view, its study from a computational
perspective still needs to be explored from a Machine Learning and
Computational Linguistics perspective.

The AMI shared task is organized according to two main sub-tasks:

Subtask A - Misogyny & Aggressive Behaviour Identification: a system must
recognize if a text is misogynous or not, and in case of misogyny, if it
expresses an aggressive attitude.

Subtask B - Unbiased Misogyny Identification: a system must discriminate
misogynistic contents from the non-misogynistic ones, while guaranteeing the
fairness of the model (in terms of unintended bias) on a synthetic dataset.

During the training phase, the task organizers will provide to the
participants the manually-annotated *AMI* training corpus (tweets) and a
sample of the synthetic dataset for measuring the fairness of the system. The
AMI Italian training corpus is an extended version of the previously released
corpus at AMI at EVALITA2018.

For the evaluation of the teams, the unlabelled test data will be released.
After the assessment, the labels for the test sets will be given for both
subtasks.

We encourage participation from both academic institutions and industrial
organizations. We invite the participants to fill this form
https://forms.gle/uFF3sAtMMqayiDiz9. You will receive information about how to
join the Google Group about the AMI challenge, where Datasets, Communications,
Questions/Answers and Guidelines will be provided.

Important Dates:

29 May 2020: Training data available (training period starts)
4 September 2020: Test data available, registration closes 
17 September 2020: Systems results due to organizers
27 September 2020: Results notification to participants
15 October 2020: Technical report due to organizers
25 October 2020: Reviews to participants (peer-reviews)
6 November 2020: Camera-ready due to organizers 
2-3 December 2020: EVALITA Workshop

Organizers:

Elisabetta Fersini, University of Milano-Bicocca
Debora Nozza, Bocconi University
Paolo Rosso, Universitat Politècnica de Valencia
 



Linguistic Field(s): Computational Linguistics

Subject Language(s): Italian (ita)

Language Family(ies): European Unclassified





 



------------------------------------------------------------------------------

***************************    LINGUIST List Support    ***************************
 The 2019 Fund Drive is under way! Please visit https://funddrive.linguistlist.org
  to find out how to donate and check how your university, country or discipline
     ranks in the fund drive challenges. Or go directly to the donation site:
               https://iufoundation.fundly.com/the-linguist-list-2019

                        Let's make this a short fund drive!
                Please feel free to share the link to our campaign:
                    https://funddrive.linguistlist.org/donate/
 


----------------------------------------------------------
LINGUIST List: Vol-31-1391	
----------------------------------------------------------