Ects : 3

Volume horaire : 24

Description du contenu de l'enseignement :

General introduction: aims and uses of NLP

 

Part I: translating texts into quantities

1. Tokenization, preprocessing
2. Word frequency and inverse-document frequency (tf and tf-idf)
3. Word embeddings

 

Part II: Traditional NLP methods

 

Methods used before LLMs

1. Text classification
2. Topic modelling and text summarization
3. Sentiment analysis

 

Part III: NLP with LLMs

1. Short presentation of LLMs: transformers, encoders-only models, decoders-only models
2. Text classification with LLM
3. Topic modelling and text summarization
4. Sentiment analysis
5. Generating prompt for generative LLM
6. Fine-tuning of LLM

Pré-requis recommandés :

Basic knowledge of Python, knowledge of classifications methods in Data science

Coefficient : 2 pour le M2 296 et 0,5 pour le M2 346

Compétence à acquérir :

At the end of this course, the students should:

• have a good knowledge of the main methods used in Natural Language Processing
• be able to implement these methods to data with Python
• be able to interpret the results obtained through these examples

Mode de contrôle des connaissances :

The evaluation is based on a project made by groups of two students

Bibliographie, lectures recommandées

• Albrecht, Jens, Ramachandran, Sidharth, Winkler, Christian. Blueprints for text analytics using Python machine learning-based solutions for common real world (NLP) applications, O'Reilly, 2020
• Alammar Jay and Maarten Grootendorst. Hands-On Large Language Models, Language Understanding and Generation, O'Reilly, 2024
• Useful website: Kaggle