PA153 Natural Language Processing

Faculty of Informatics
Autumn 2024
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).
In-person direct teaching
Teacher(s)
doc. Mgr. Pavel Rychlý, Ph.D. (lecturer)
RNDr. Zuzana Nevěřilová, Ph.D. (assistant)
Guaranteed by
doc. Mgr. Pavel Rychlý, Ph.D.
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
Mon 23. 9. to Mon 16. 12. Mon 12:00–13:50 D1
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 33 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.
The course is also listed under the following terms Autumn 2002, Autumn 2003, Autumn 2004, Autumn 2005, Autumn 2006, Autumn 2007, Autumn 2008, Autumn 2009, Autumn 2010, Autumn 2011, Autumn 2012, Autumn 2013, Autumn 2014, Autumn 2015, Autumn 2016, Autumn 2017, Autumn 2018, Autumn 2019, Autumn 2020, Autumn 2021, Autumn 2022, Autumn 2023.
  • Enrolment Statistics (recent)
  • Permalink: https://is.muni.cz/course/fi/autumn2024/PA153