PA153 Natural Language Processing
Faculty of InformaticsAutumn 2022
- Extent and Intensity
- 2/0/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
- Teacher(s)
- doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
- Guaranteed by
- prof. PhDr. Karel Pala, CSc.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. Mgr. Pavel Rychlý, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics - Timetable
- Fri 8:00–9:50 A217
- Course Enrolment Limitations
- The course is also offered to the students of the fields other than those the course is directly associated with.
- fields of study / plans the course is directly associated with
- there are 56 fields of study the course is directly associated with, display
- Course objectives
- The course offers a deeper knowledge about the natural language processing using statistical algorithms and/or deep learning of neural networks. Working examples and applications are provided to illustrate selected methods.
- Learning outcomes
- The students will learn about practical processing of texts.
The students will be able to:
- understand text processing methods;
- design algorithms for classification of text, documents, sentences;
- understand the structure of question answering and machine translation systems;
- evaluate the quality of the natural language processing applications. - Syllabus
- text processing, tokenization, corpora
- word counts, n-grams, language modeling
- text classification
- information extraction
- tagging, parsing
- information retrieval, question answering
- parallel text, word alignment, machine translation
- continues spaces representations
- recurent neural networks for language modeling
- sequence processing, transformers
- neural machine translation
- natural language generation, huge language models
- Literature
- recommended literature
- GOODFELLOW, Ian, Yoshua BENGIO and Aaron COURVILLE. Deep learning. London, England: MIT Press, 2016, xxii, 775. ISBN 9780262035613. info
- JURAFSKY, Dan and James H. MARTIN. Speech and language processing : an introduction to natural language processing, computational linguistics and speech recognition. 2nd ed. New Jersey: Pearson, 2009, 1024 s. ISBN 9780135041963. info
- Teaching methods
- Teaching is performed in the form of oral lectures and seminars, in which the slides and demos of the relevant software tools are combined. Students work out homeworks or smaller projects. At the appropriate points of the teaching the open dialog between a teacher and students is used.
- Assessment methods
- It is possible to get 50 points at the final written test. At least 25 points are needed to pass. It is possible to get at most 25 points from the optional home works or projects.
- Language of instruction
- English
- Further Comments
- Study Materials
The course is taught annually.
- Enrolment Statistics (Autumn 2022, recent)
- Permalink: https://is.muni.cz/course/fi/autumn2022/PA153