Скачать или смотреть #2025TEF

ALL IN ONE: HOW TO EVALUATE THE QUALITY OF AI-GENERATED CONTENT

Panel chair:  Ingemar STRANDVIK (DG Translation)
Agustín DA FIENO DELUCCHI (Director of Globalisation, AI and Data Science, Microsoft)
Kateřina GAŠOVÁ (Global Quality Solutions Strategist, Argos Multilingual)
Pavel SOUKENÍK (Head of Global Solutions, Acolad) 
The speakers will explore challenges to the current approaches available to evaluate the quality of AI-generated content.

Today, we witness multimodal technologies heavily involved in target content delivery, whereas the quality evaluation framework hasn’t yet been adapted. We’ll unveil and demonstrate a newly developed framework for evaluating multimodal and AI-generated content.

The discussion will explore the integration of text, images, audio and interactivity, emphasising the holistic nature of this novel approach to ensuring high standards of relevance, accuracy, user engagement and cultural sensitivity. 

Examples of the new evaluation framework will help illustrate and explain these holistic principles, along with specific evaluation cases – with the aim of inspiring the audience when it comes to designing and performing actual measurements.