Retour

Large Language Models

ECTS : 4

Volume horaire : 24

Description du contenu de l'enseignement :

The course focuses on modern and statistical approaches to NLP.

Natural language processing (NLP) is today present in some many  applications because people communicate most everything in language :  post on social media, web search, advertisement, emails and SMS,  customer service exchange, language translation, etc. While NLP heavily  relies on machine learning approaches and the use of large corpora, the  peculiarities and diversity of language data imply dedicated models to  efficiently process linguistic information and the underlying  computational properties of natural languages.

Moreover, NLP is a fast evolving domain, in which cutting-edge  research can nowadays be introduced in large scale applications in a  couple of years.

The course focuses on modern and statistical approaches to NLP: using  large corpora, statistical models for acquisition, disambiguation,  parsing, understanding and translation. An important part will be  dedicated to deep-learning models for NLP.

- Introduction to NLP, the main tasks, issues and peculiarities
- Sequence tagging: models and applications
- Computational Semantics
- Syntax and Parsing
- Deep Learning for NLP: introduction and basics
- Deep Learning for NLP: advanced architectures
- Deep Learning for NLP: Machine translation, a case study

Compétence à acquérir :



Université Paris Dauphine - PSL - Place du Maréchal de Lattre de Tassigny - 75775 PARIS Cedex 16 - 21/11/2024