Navigation

13M111OPJ - Natural language processing

Course specification
Course title Natural language processing
Acronym 13M111OPJ
Study programme Electrical Engineering and Computing
Module Software Engineering
Type of study master academic studies
Lecturer (for classes)
Lecturer/Associate (for practice)
Lecturer/Associate (for OTC)
ESPB 6.0 Status elective
Condition None
The goal Introduce students to the basic concepts and techniques of statistical Natural language processing (NLP). A comparative analysis of used machine learning methods. Presentation of the main morphological, syntactic and semantic problems in the computer NLP. During the course, students will study the implementation of the popular models of these types of applications.
The outcome Students will be able to recognize a problem that belongs to the field Natural language processing (NLP), and based on their knowledge apply the most appropriate and most effective method for its solution.
Contents
URL to the subject page http://rti.etf.bg.ac.rs/rti/ms1opj/
Contents of lectures Machine learning in natural language processing. Generative and discriminant models. Sequence models. Overview of the morphological, syntax, and semantic problems. Linguistic models. Stemming and lemmatization. Marking word types. Parsing. Text classification based on thematic and sentiment. Lexical semantics. Distributional semantics. Semantic similarity. Recognition of entities.
Contents of exercises Laboratory demonstration exercises. Common conception and elaboration of topic and project content; referral to relevant concepts, approaches, tools and literature; monitoring and discussing the solutions, results and possible improvements during project work and its documenting.
Literature
  1. Dan Jurafsky, James H. Martin, "Speech and Language Processing", Prentice Hall, 2008. (Original title)
  2. Christopher D. Manning, Prabhakar Raghavan, Hinrich Schütze, "An Introduction to Information Retrieval", Cambridge University Press, 2008. (Original title)
Number of hours per week during the semester/trimester/year
Lectures Exercises OTC Study and Research Other classes
2 2 1
Methods of teaching Lectures, presentations, practical exercises, individual work on projects,
Knowledge score (maximum points 100)
Pre obligations Points Final exam Points
Activites during lectures Test paper 30
Practical lessons Oral examination
Projects 70
Colloquia
Seminars