11:00
12:30
Transformers applied to NLP: presentation and implementation.
Since their introduction in 2017, neural networks known as Transformers have revolutionised the state of the art in natural language processing.
In particular, these architectures have made it possible to train linguistic models that excel in tasks such as translation, text generation, and summarisation.
This presentation will consist of a theoretical part detailing their architecture and operation, followed by a practical part illustrated by the implementation of a model in PyTorch.
Amphi LaBRI