Rīgas Tehniskā universitāte                                                                                                         29.01.2023 18:00
                                                          RTU Course "Natural Language Processing"
                                                                                12308 null
           General data
           Code                                              DIP719
           Course title                                      Natural Language Processing
           Course status in the programme                    Compulsory/Courses of Limited Choice
           Responsible instructor                            Gints Jēkabsons
           Volume of the course: parts and credits points    1 part, 4.0 Credit Points, 6.0 ECTS credits
           Language of instruction                           LV, EN
           Annotation                                        Natural language processing is an interdisciplinary field that studies methods and models enabling
                                                             computers to process, understand, and generate human (natural) language.
                                                             Within this study course, students learn the main concepts of natural language processing, its
                                                             various practical applications and the methods used to implement them, as well as the skills for
                                                             evaluation and interpretation of the obtained results. For solving practical natural language
                                                             processing tasks, students learn appropriate software tools.
           Goals and objectives of the course in terms of    The aim of the study course is to provide students with the theoretical and practical knowledge in
           competences and skills                            natural language processing and its practical applications.
                                                             The tasks of the study course:
                                                             * to develop students’ understanding of the basic concepts of natural language processing and the
                                                             tasks it solves;
                                                             * to develop students’ skills to identify and choose natural language processing methods suitable
                                                             for solving specific tasks;
                                                             * to improve students’ skills to apply these methods in practice, as well as to evaluate and interpret
                                                             the obtained results;
                                                             * to develop students’ skills to use software tools appropriate to specific natural language
                                                             processing problems.
           Structure and tasks of independent studies        Individual assignments involve solving theoretical and practical tasks where students apply the
                                                             knowledge acquired during the course on natural language processing, its methods, and
                                                             appropriate software tools.
           Recommended literature                            Obligātā. / Obligatory:
                                                             Steven Bird, Ewan Klein, Edward Loper. Natural Language Processing with Python
                                                             (http://www.nltk.org/book/)
                                                             Dan Jurafsky, James H. Martin. Speech and Language Processing 3rd ed. draft Prentice Hall,
                                                             2021, 1032 p. (http://web.stanford.edu/~jurafsky/slp3/)
                                                             Papildu. / Additional:
                                                             Al Sweigart. Automate the Boring Stuff with Python: Practical Programming for Total Beginners
                                                             No Starch Press, 2015 (https://automatetheboringstuff.com/)
                                                             Christopher Manning, Hinrich Schütze. Foundations of Statistical Natural Language Processing
                                                             MIT Press, Cambridge, MA, 1999, 655 p.
                                                             Alexander Clark, Chris Fox, Shalom Lappin (eds.). The Handbook of Computational Linguistics
                                                             and Natural Language Processing Wiley-Blackwell, 2010, 802 p.
                                                             Anne O'Keeffe, Michael McCarthy (eds.). The Routledge Handbook of Corpus Linguistics
                                                             London: Routledge, 2010, 682 p.
           Course prerequisites                              Python programming fundamentals.
           Course contents
           Content                                                                                                 Full- and part-time     Part time extramural
                                                                                                                    intramural studies           studies
                                                                                                                   Contact      Indep.     Contact      Indep.
                                                                                                                    Hours       work        Hours       work
           Main concepts of natural language processing.                                                              6           9           0           0
           Methods and applications of natural language processing related to syntax (text segmentation,              16          24          0           0
           lemmatization, stemming, part-of-speech tagging, terminology extraction a.o.).
           Methods and applications of natural language processing related to semantics (word sense                   20          30          0           0
           disambiguation, topic modeling, text classification, sentiment analysis a.o.).
           Evaluation and interpretation of obtained results.                                                         6           9           0           0
           Software tools for natural language processing.                                                            16          24          0           0
                                                                                                          Total:      64          96          0           0
           Learning outcomes and assessment
           Learning outcomes                                                                                      Assessment methods
           Able to demonstrate knowledge in main concepts of natural language processing                          Individual assignments, exam.
           Able to identify and choose appropriate methods for solving specific natural language processing       Individual assignments, exam.
           problems.
           Able to apply specific natural language processing methods as well as evaluate and interpret           Individual assignments, exam.
           obtained results.
           Able to apply software tools for solving natural language processing problems.                       Individual assignments, exam.
          Evaluation criteria of study results
           Criterion                                                                                                                             %
           Individual assignments                                                                                                                80
           Exam                                                                                                                                  20
                                                                                                                               Total:           100
          Study subject structure
              Part          CP                                Hours per Week                                                    Tests
                                            Lectures              Practical              Lab.                Test              Exam                Work
               1.           4.0                2.0                  0.0                   2.0                                     *