[DMANET] Final Call-for-Participation: TalentCLEF2026 Workshop/Lab (CLEF2026) - Shared tasks on multilingual job and skill intelligence for next-generation HR systems.

(* apologies for cross-posting *) Final Call for Participation TalentCLEF Workshop/Lab (CLEF 2026) Shared task on multilingual job and skill intelligence for next-generation HR systems. 📅 Registration Deadline: April 23, 2026 https://talentclef.github.io/talentclef/ Overview The labor market is changing faster than ever: skills evolve in years, job roles shift continuously, and organizations operate across languages and borders. At the same time, the use of Artificial Intelligence in Human Resources is rapidly expanding, transforming how talent is identified, matched, and developed. However, this growing adoption also highlights a critical need for public benchmarks and standardized evaluation frameworks that enable reproducibility, fair comparison, and robust development of NLP systems in Human Capital Management. TalentCLEF 2026 invites the community to address these challenges through shared tasks on skill and job intelligence, fostering the development of accurate, multilingual, and practically applicable solutions for Human Capital Management Key information: - Web: https://talentclef.github.io/talentclef/ - Data: https://doi.org/10.5281/zenodo.17625261 - Codabench Task A: https://www.codabench.org/competitions/14226/ - Codabench Task B: https://www.codabench.org/competitions/14489/ - Registration: https://clef-labs-registration.dipintra.it/ Why participate? - Evaluate your models on realistic Human Capital Management tasks - Work with multilingual and cross-lingual data (English and Spanish) - Access open, privacy-preserving datasets - Contribute to an emerging benchmark in HR/NLP - Publish a system description paper in CLEF Working Notes (CEUR-WS) - Present your work at CLEF 2026 in Jena, Germany Tasks Overview TalentCLEF 2026 is structured into two independent but complementary tasks, allowing participants to compete in one or both. - Task A - Contextualized Job-Person Matching: - Goal: Rank candidate résumés for a given job offer. - This task focuses on context-aware matching between full job descriptions and candidate profiles. It is framed as an information retrieval problem, where systems must return a ranked list of résumés ordered by relevance. - The task includes English, Spanish, and cross-lingual settings, reflecting real-world recruitment scenarios. - Task B - Job-Skill Matching with Skill Type Classification: - Goal: Identify and classify relevant skills for a given job title. - Participants must retrieve skills from a predefined gazetteer and classify each skill as: Core (required) and Contextual (optional). - This task emphasizes skill-based representations and the nuanced role of skills within job profiles. Important Dates - 2nd February 2026 - Development data available for Tasks A - 2nd February 2026 - Training data available for Task B - 16th February 2026 - Development data available for Task B - 2nd March 2026 - Codabench Release for Task A and Task B - 20th April - 3rd May 2026 - Evaluation Period for Task A and Task B - 23rd April - Official registration deadline - 7th May 2026 – Publication of Official Results - 30th May 2026 – Submission of CLEF 2026 Participant Working Notes (CEUR-WS) - 27th June 2026 - Notification of Acceptance for Participant Papers Workshop and Proceedings Teams participating in TalentCLEF will be invited to submit a system description paper for the CLEF 2026 Working Notes proceedings, published on CEUR-WS. The TalentCLEF 2026 workshop will be co-located with CLEF 2026 and held in Jena, Germany, from September 21 to 24, 2026. Participants will have the opportunity to present their approaches at the workshop. Main Organizers - Luis Gascó, Avature - Hermenegildo Fabregat, Avature - Laura García-Sardiña, Avature - Paula Estrella, Avature - Casimiro Pío Carrino, Avature - Jens-Joris Decorte, TechWolf - Matthias De Lange, TechWolf - Warre Veys, TechWolf - Daniel Deniz Cerpa, Avature - Álvaro Rodrigo, Universidad Nacional de Educación a Distancia (UNED) - Rabih Zbib, Avature ********************************************************** * * Contributions to be spread via DMANET are submitted to * * DMANET@zpr.uni-koeln.de * * Replies to a message carried on DMANET should NOT be * addressed to DMANET but to the original sender. The * original sender, however, is invited to prepare an * update of the replies received and to communicate it * via DMANET. * * DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET) * http://www.zaik.uni-koeln.de/AFS/publications/dmanet/ * **********************************************************