General Claim detection model - LESA
LESA: Linguistic Encapsulation and Semantic Amalgamation Based Generalised Claim Detection from Online Content
Welcome to the AI Assets Catalog! Here you can browse, search and download all the assets currently indexed in the AI-on-Demand platform, including AI libraries, datasets, containers, and more. You are welcome to publish your own AI assets here! To do so, log in in to the platform, go to your dashboard and use the Submit new content button to access the submission forms.
LESA: Linguistic Encapsulation and Semantic Amalgamation Based Generalised Claim Detection from Online Content
XLM-RoBERTa model which was trained during experiments in order to create models capable of detecting check-worthy claims in the widest achievable range.
mDeBERTa V3 model which was trained during experiments in order to create models capable of detecting check-worthy claims in the widest achievable range.
The General Claim dataset is a diverse, harmonized dataset created for the task of check-worthy claim detection, addressing the limitations of narrow, specialized datasets currently used in the field. Constructed from five pre-existing datasets, it emphas...
The EU’s six AI Networks of Excellence (NoEs) – AI4Media, ELISE, ELSA, euROBIN, HUMANE-AI, and TAILOR – have jointly published a revised and updated version of the Joint Strategic Research Agenda (SRA) in 2024.
Python script implemented to automate the extraction of STEP file’s orthogonal projections using tools available on PIXYZ Studio software.
This experimental AI-powered service automatically extracts representative keyframes from a video. The service also identifies and improves the resolution of faces and text detected within the keyframes for better clarity.
A high-performing synthetic image detection method that utilises intermediate layers of the CLIP image encoder.