Objectives and competences
The objective of this course is that students will be able to develop, test, and evaluate systems for natural language processing.
Content (Syllabus outline)
• Introduction: an overview of natural language processing and basic text processing.
• Language modeling: probabilistic languages models, language model evaluation, and smoothing.
• Spelling Correction: non-word spelling errors and real-word spelling errors.
• Text classification: methods for text classification and evaluation of classification methods.
• Sentiment analysis: basic methods for sentiment analysis and sentiment lexicons.
• Semantics and WordNet: building semantic structures, semantic interpretation, meaning.
• Statistical machine translation: basic methods for the statistical machine translation and evaluation of machine translation.
• Information extraction and named entity recognition.
• Advanced language technologies.
Learning and teaching methods
• Lectures: in lectures, students get to know the theoretical contents of the course. Lectures are conducted as classical lectures in frontal form, interleaved with discussions on practical examples of language technology.
• Tutorials: in tutorial exercises, students are informed about lab work.
• Lab work: in laboratory exercises, students work on individual tasks of language technologies with the help of scientific literature.
Intended learning outcomes - knowledge and understanding
• describe major trends in natural language processing,
• develop, test, and evaluate systems for natural language processing,
• create different corpora,
• explain the importance of pragmatics in language technologies,
• describe several standard methods for natural language processing
Intended learning outcomes - transferable/key skills and other attributes
• Communication skills: oral lab work defence, manner of expression at written examination.
• Use of information technology: use of appropriate algorithms and software tools for natural language processing tasks.
Readings
• Ekman, M. (2022). Learning deep learning: theory and practice of neural networks, computer vision, natural language processing and transformers using tensorflow (1st ed., p. LIII, 688). Addison-Wesley.
• Koehn, P. (2011). Statistical machine translation (Repr. with corr., p. XII, 433). Cambridge Univ. Press.
• Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python (p. XX, 479). O’Reilly.
• Jurafsky, D., & Martin, J. H. (2000). Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition (p. XXVI, 934). Prentice Hall.
• Natural Language Processing and Text Mining. (2007). Springer. http://link.springer.com/book/10.1007/978-1-84628-754-1
• Manning, C. D., & Schütze, H. (1999). Foundations of statistical natural language processing (p. XXXVII, 680). MIT Press.
Additional information on implementation and assessment The exam may be replaced by written midterm examinations in the weight of 50%.
