NLP

Natural language processing

Description: This course explores the fundamentals of automatic natural language processing (ANNP), covering topics such as word embeddings, language models, recurrent and recursive neural networks and transformers, enabling students to master text analysis and generation.

Content: This course introduces the main linguistic theories used to model natural language (e.g. formal grammars, dependency grammars, etc.). It presents the various natural language processing (NLP) tools available and the statistical models on which they are based. Particular emphasis will be placed on the deep learning methods that constitute the state of the art for most NLP tasks.

Learning outcomes: By the end of this course, participants will have acquired a thorough understanding of the fundamental concepts of NLP. They will be able to apply text preprocessing techniques to clean and organize linguistic data, as well as use pre-trained language models for various tasks such as text classification, text generation, machine translation. Learners will be proficient in the use of popular natural language processing libraries such as NLTK, SpaCy, Transformers.

Teaching methods: Each session will include a lecture part during which new concepts will be introduced, followed by a practical work session. Practical work sessions will be direct applications concepts seen in lectures. All teaching materials will be provided to students.

Evaluation methods: 2h written test, can be retaken.

Evaluated skills:

• Be operational, responsible, and innovative in the digital world

Course supervisor: Joël Legrand

Geode ID: 3MD4150