Home / Academics / List of courses /

Natural language processing

Associate teachers


ECTS credits


Number of hours: Lectures + Seminars + Exercises

15 / 15 / 15

Course objectives

Students will gain knowledge and skills in the area of computational processing of natural languages and will be able to independently model the procedures of lexical and syntactic analysis of natural languages.

They will also be able to use tools to extract information from texts. NooJ NLP environment will be used to demonstrate Finite-State Automata (FSA), Recursive Transition Networks (RTNs), Enhanced Recursive Transition Networks (ERTNs), Context-Free Grammars (CFGs) and Context-Sensitive Grammars (CSGs). Perl and NooJ Regular Expressions will be used for unstructured text querying. Local grammars will be built via graph and rule editors (inflectional, derivational, lexical, orthographical, morphological, terminological, syntactic, semantic and translation grammars).

Disambiguation of results and building Concordances will be exemplified. Algorithms will be evaluated (precision, recall, f-measure) and compared. NLP in Big Data context will be discussed.

Enrolment requirements and/or entry competences required for the course


Learning outcomes at the level of the programme to which the course contributes

  • Explain major historical paradigms and recognize important new trends in cognitive science.
  • Apply specific knowledge and skills from selected disciplines constituting cognitive science.
  • Critically evaluate cognitive science findings and synthesize information to be employed in a collaborative professional environment.
  • Participate in data-driven innovation projects and apply appropriate data science tools.
  • Apply AI tools in concrete tasks and practical contexts.

Course content (syllabus)

  • What is NLP and what does it do?
  • Corpora; Evaluation and measures (gold standard, PARSEVAL, precision, recall, f-measure).
  • Use of language processing tools; Graphical vs textual grammar interface.
  • Queries over texts.
  • POS tagging: statistical and non-statistical approach.
  • POS tagging and dictionaries.
  • Inflectional and derivational grammars (description of paradigms).
  • Nested rules.
  • Word generation; Recognizing new words from existing ones.
  • Productive morphology (special labels in the identifier/signifier; equality check operation; variables; results and error finding).
  • Multiword expressions (vocabulary, grammar); language variations.
  • Regular grammars; Regular expressions.
  • Context free grammars.
  • Context grammars.
  • NLP expert systems in the analysis of social media.

Student responsibilities

Class attendance. Independent assignments. Actively participate in group assignments and classroom activities.

Required literature

  • Daniel Jurafsky, James H. Martin (2019). Speech and Language Processing (3rd edition). Prentice Hall, USA.
  • Alexander Clark, Chris Fox, Shalom Lappin (2010). The Handbook of Computational Linguistics and Natural Language Processing. Wiley-Blackwell, USA.
  • Christopher D. Manning, Hinrich Schütze (1999). Foundations of Statistical Natural Language Processing. MIT Press, USA.

Optional literature

  • -