Natural Language Processing

Course Description

Theoretical fundamentals of natural language processing. Language collections: dictionaries and corpora, markup systems. Learning from the corpus: learning new words, solving ambiguity problems, language models. Grammar: Hidden Markov models (HMM), context-independent grammar (CFG) and others. Application of grammatical models in corpus markup and parsing. Linguistic pre-processing in speech synthesis. Language post-processing in speech recognition. Methods and tools for machine translation. The impact of natural language processing applications on social development and language change.

Learning Outcomes

  1. identify computational complexity of NLP problems
  2. evaluate open source NLP tools
  3. manipulate text and speech corpora
  4. participate in speech synthesis projects
  5. participate in speech recognition projects
  6. participate in machine translation projects

Forms of Teaching


Independent assignments

Week by Week Schedule

  1. Computational semantics (formal semantics, semantic role labeling)
  2. Computational morphology
  3. Part of speech tagging
  4. Deterministic and stochastic grammars, constituency and dependency grammars (CFG, PCFG)
  5. Parsing algorithms (CYK, Chart), lexicalized parsing, dependency parsing
  6. Distributional semantic models
  7. Corpus-based methods, n-grams, collocations
  8. Language models, smoothing, evaluation
  9. Midterm exam
  10. Machine translation
  11. Graph based NLP: semantics; syntax and applications
  12. Natural language processing applications with regional or social dimensions
  13. Applications of social network analysis to understand language variation and change
  14. Project
  15. Final exam

Study Programmes

University graduate
Computer Engineering (profile)
Recommended elective courses (3. semester)
Computer Science (profile)
Recommended elective courses (3. semester)
Software Engineering and Information Systems (profile)
Recommended elective courses (3. semester)
Telecommunication and Informatics (profile)
Recommended elective courses (3. semester)


(.), Daniel Jurafsky, James H. Martin (2019.), Speech and Language Processing (3nd edition), Prentice Hall,
(.), Christopher D. Manning, Hinrich Schütze (1999.), Foundations of Statistical Natural Language Processing, MIT Press,
(.), Ruslan Mitkov (ed.) (2005.), The Oxford Handbook of Computational Linguistics, Oxford University Press, USA,
(.), Shrikanth Narayanan, Abeer Alwan (2004.), Text to Speech Synthesis: New Paradigms and Advances, Prentice Hall PTR,

For students


ID 222553
  Winter semester
L3 English Level
L1 e-Learning
30 Lectures
6 Exercises
15 Laboratory exercises