ECUE Advanced NLP

Code de l'ECUE : SMENLP

Ce cours appartient à UE AIA (Artificial Intelligence and Applications) (6 ECTS) qui contient 3 ECUE

Structure

EUR DS4H

Domaine disciplinaire

Informatique

Lieu d'enseignement

Campus SophiaTech Les Lucioles

Niveau du cours

Master 2

Semestre

Semestre impair

Langue

Anglais , Français

PRESENTATION

Automatic Natural Language Processing (NLP) is a branch of Artificial Intelligence (AI) that enables computers to understand and generate human language. NLP enables us to talk to our phones, use the web to answer questions, organize discussions in books and social media, and even translate between human languages. Because language is rich, ambiguous and very difficult for computers to understand, these systems can sometimes seem magical, but they are engineering problems that we can solve with data, mathematics and linguistic knowledge.

This course will deal generally with deep learning methods for natural language processing, with a particular focus on Large Language Models (LLMs). We will cover modeling architectures and downstream tasks such as text classification, question answering, machine translation and text generation.

Responsable(s) du cours

Sofiane Elguendouze

Présentiel

12h de cours magistral
16h de travaux dirigés

PREREQUIS

Avant le début du cours, je dois ...

Basics in machine learning and natural language processing.

OBJECTIFS

A la fin de ce cours, je devrais être capable de...

1) Understand modern neural network algorithms for linguistic information processing.
2) Move from simple word representation and syntactic processing to more robust representation, as well as the implementation of complex deep learning models for a variety of NLP tasks (such as question answering, machine translation and text generation).

CONTENU

Introduction & background

Aucune description
Neural networks & Back-propagation

Aucune description
Recurrent Neural Networks & Encoder-Decoder

Aucune description
Attention & Transformers

Aucune description
Pre-training, Finetuning & LLMs

Aucune description
Interpretability in NLP

Aucune description

Accéder au Syllabus complet (Authentification requise)

Important

Ce syllabus n’a aucune valeur contractuelle. Son contenu est susceptible d’évoluer en cours d’année : soyez attentifs aux dernières modifications.