[Corpora-List] Call for participation: SemEval 2022 shared task on Patronizing and Condescending Language Detection

Luis Espinosa Anke luis.espinosa83 at gmail.com
Thu Sep 30 17:12:43 CEST 2021


Apologies for cross-posting

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

CALL FOR PARTICIPATION

Welcome to SemEval 2022 Task 4: Patronizing and Condescending Language Detection

We invite all researchers interested in text classification, bias detection and NLP for social impact to participate in SemEval 2022 - Task 4, which is focused on detecting and categorizing Patronizing and Condescending Language (PCL) towards vulnerable communities.

Detailed information about the task can be found in the following links:

-

Task website: https://sites.google.com/view/pcl-detection-semeval2022

-

Codalab: https://competitions.codalab.org/competitions/34344

-

Github (with starter code):

https://github.com/Perez-AlmendrosC/dontpatronizeme

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

What is PCL and why is it important?

Somebody is patronizing or condescending when their language denotes a superior attitude towards others, talks down to them, or describes them or their situation in a charitable way, raising a feeling of pity and compassion. In the media, vulnerable communities seem to be the perfect target for charity and pity-driven texts which lead to condescension and patronization towards these under-represented groups.

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

The task

The aim of this task is to identify PCL, and to categorize the linguistic techniques used to express it, specifically when referring to communities identified as being vulnerable to unfair treatment in the media.

Participants are provided with sentences in context (paragraphs), extracted from news articles, in which one or several predefined vulnerable communities are mentioned. The challenge is divided into two subtasks:

Subtask 1: Binary classification. Given a paragraph, a system must predict whether or not it contains any form of PCL.

Subtask 2: Multi-label classification. Given a paragraph, a system must identify which PCL categories (if any) express the condescension.

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

Important Dates

Training data available: September 3, 2021

Evaluation starts: January 10, 2022

Evaluation ends: (TBC) January 31, 2022

Paper submissions due: (TBC) February 23, 2022

Notification to authors: March 31, 2022

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

Organisers

Carla Perez-Almendros, Cardiff University, UK

Luis Espinosa-Anke, Cardiff University, UK

Steven Schockaert, Cardiff University, UK -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 13702 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20210930/63373c63/attachment.txt>



More information about the Corpora mailing list