DIMEMEX @ IberLEF 2025: Call for Participation
Participate in DIMEMEX @ IberLEF 2025, a challenge focused on detecting abusive content in Mexican Spanish memes. CodaLab site now available.
The DIMEMEX (Detection of Inappropriate Memes from Mexico) challenge at IberLEF 2025 is now open for participation. This event focuses on the detection of abusive content in Mexican Spanish, particularly hate, offensive, and vulgar memes.
The CodaLab site for accessing the details of the DIMEMEX-2025 tasks is now available at CodaLab URL.
Task Description:
- Three-way classification: hate speech, inappropriate content, or neither.
- Fine-grained classification: to discriminate instances containing hate speech into different categories such as classism, sexism, racism, and others.
- Three-way classification with LLMs: Same as the first task, but participants are restricted to exclusively leveraging LLMs to detect the specified categories.
Important Dates:
- March 4th – Release of training corpora (Now available!)
- April 15th – Release of test corpora and start of evaluation campaign.
- April 29th – End of evaluation campaign (deadline for submission of runs).
- May 6th – Publication of official results.
- May 20th – Deadline for paper submission.
- June 3rd – Acceptance notification.
- June 17th – Camera-ready submission deadline.
- September – TBD Publication of proceedings.
- September – TBD IberLEF at SEPLN 2025 Workshop.
For more information, visit the DIMEMEX 2025 website.
Tags: DIMEMEX, IberLEF 2025, abusive content detection, multimodal models, Mexican Spanish, hate speech