Automatic language processing – Faculty of Letters

  • Course (CM)
  • Integrated Courses (CI)
  • Tutorials (TD)
  • Practical work (TP)
  • Student work (TE)

Teaching language: French

Description of teaching content

Introduction to Automatic Language Processing (S6 License)


Automatic language processing (TAL): definition, challenges, historical evolution. Automatic analysis and generation. Symbolic approach in NLP at several levels: morpho-syntax, lemmatization, formal grammars (HPSG or LFG or another system that can define rules). Automatic syntactic analysis: constituent analysis and dependency analysis. Rule-based systems for discourse analysis. Learning approach. Labeled and annotated data and annotation problem.
Example of applications: information retrieval, neology generation platforms, resources for poorly endowed languages, terminology extraction

Skills to acquire

At the end of this course, students will be able to:

  • master basic notions in Automatic Language Processing
  • use an annotation tool (Unitex) and create resources for it

Bibliography, recommended reading

Habert, B. 2005. Instruments and electronic resources for French. Paris: Ophrys
Jurafsky, D. and Martin, J., 2008. Speech and Language Processing : An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition. Prentice Hall
Manning, C, and Schütze, H, 1999 Foundations of Statistical Natural Language Processing. The MIT Press
Mitkov, R. 2005. The Oxford Handbook of Computational Linguistics. Oxford University Press