Deep Learning advanced
NLP
(3 days)

❬Back to trainings

Natural language processing is a full-fledged field of artificial intelligence at the intersection of computer science, mathematics, linguistics and cognitive science. The goal is to build applications capable of analyzing, modeling, understanding and imitating human language.
Since the 1950s, from the Turing test to the creation of the first conversational agents such as the ELIZA chatbot, NLP has gradually become more sophisticated. Real advances have taken place with the implementation of Machine Learning and Deep Learning models allowing to address a large set of syntax, semantic, speech and language tasks.
Nowadays, NLP is everywhere, whether in machine translation tools, spell checking, writing assistance, automatic text generation, speech recognition, etc.

You already know the basic principles of Deep Learning and you have already implemented different neural network architectures, but you want to know more about the opportunities offered by Deep Learning in the field of NLP, this training is for you.

Goals

• Set up an efficient preprocessing of a textual dataset
• Master the architectures of recurrent neural networks and transformers
• Implement concrete cases for each type of network
• Reuse existing models with transfer learning
• Measure the relevance of the implemented models & Visualize the learning

Teaching method

• This training is 70% practical and uses illustrated and didactic exercises.
• A daily evaluation of the acquisition of the knowledge of the day before is carried out.
• A synthesis is proposed at the end of the training.
• An evaluation will be proposed to the trainee at the end of the course.
• A course support will be given to each participant including slides on the theory and exercises.
• A sign-in sheet for each half-day of attendance is provided at the end of the course as well as a certificate of completion if the trainee has attended the entire session.
• A follow-up and an exchange with the participants will take place a few days after the training.

Prerequisite

• Trainees must have experience in Deep Learning or have followed the Workshop Deep Learning training (mastery of Machine Learning concepts and have implemented different neural network architectures: convolutional, recurrent, ...)
• Knowledge of Python, scientific libraries (scikit learn, pandas, numpy) and the Deep Learning framework TensorFlow is required.

Program

Introduction

Text Normalization

Text vectorization

Recurrent Neural Networks

Transformers