CORDIS Project
Funding breakdown and partner intelligence are Premium
Sign in and upgrade to Premium for EU contribution totals, consortium analytics, OpenAlex research context, and AI summaries. · 0 consortium intelligence fields visible of 1
Start free • Cancel anytime • 14-day refund guarantee
This project aims to enhance natural language processing by addressing the shortcomings of current deep learning models. It focuses on improving out-of-domain generalization, contextual information usage, and memory traceability through interdisciplinary methods from machine learning, cognitive science, and information…
In recent years, transformer-based deep learning models such as BERT or GPT-3 have led to impressive results in many natural language processing (NLP) tasks, exhibiting transfer and few-shot learning capabilities.However, despite faring well in benchmarks, current deep learning models for NLP often fail badly in the wild: they are bad at out-of-domain generalization, they do not exploit contextual information, they are poorly calibrated, and their memory is not traceable.
These limitations stem…
INSTITUTO DE TELECOMUNICACOES
Partner organizations (coordinator is shown above), with normalized type and CORDIS activity type. Guests see up to 4 partners.
Portugal, Porto Alto
Type: SME
Activity type: Private for-profit entities (excluding Higher or Secondary Education Establishments)
SME: Yes
Similar projects, consortium collaboration history, frequent partners, and OpenAlex research context.
Guests see up to 5 topics.
Guests see up to 5 keywords.
