INF582 - Natural Language Processing

Computer Science M1 programme (PA-info), École Polytechnique

Information

This course is in English. Part of the INF582 module in collaboration with Michalis Vazirgiannis.

Syllabus (for my part of the course):

  • Lexical statistics and language models (n-gram models; neural language models)
  • Sequence labelling: Named Entity Recognition, Part Of Speech tagging using Hidden Markov Models and Conditional Random Fields
  • Knowledge and Knowledge Representation: Knowledge Graph embeddings (TransE and similar methods)
  • Modern LLM problems: detection of generated text, privacy issues and hallucinations

Note: all material is available on the IP Paris Moodle; this page is just for reference.

Additional material

  • D. Jurafsky and H. Martin: Speech and Language Processing (draft available online)
  • Y. Goldberg: Neural Network Methods for Natural Language Processing