PLIN037 Semantic Computing

Faculty of Arts
Spring 2024
Extent and Intensity
0/2/0. 4 credit(s). Type of Completion: z (credit).
Taught partially online.
Teacher(s)
RNDr. Zuzana Nevěřilová, Ph.D. (lecturer)
Guaranteed by
RNDr. Zuzana Nevěřilová, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics
Timetable
Thu 10:00–11:40 G13, except Thu 18. 4.
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
The capacity limit for the course is 30 student(s).
Current registration and enrolment status: enrolled: 6/30, only registered: 0/30, only registered with preference (fields directly associated with the programme): 0/30
fields of study / plans the course is directly associated with
Course objectives
At the end of the course, students should be able to understand terms from the field of computer natural language processing on the semantic level; use existing knowledge bases and know their advantages and drawbacks; understand the term linked open data; use the languages of the Semantic web; understand semantic networks; understand and explain the principle of inference in semantic networks; interpret probabilistic models of meaning; understand semantic modeling using word embeddings; understand and explain anaphora resolution issues and algorithms for automatic anaphora resolution; understand the discourse analysis; understand how semantics is contained in large language models; understand how to evaluate models
Learning outcomes
The student will be able to:
- identify a natural language processing problem as a problem of semantic processing,
- name traditional approaches to natural language semantics,
- name and describe existing knowledge bases,
- select and apply a particular knowledge base to a particular problem,
- select and apply a particular pre-trained model to a particular problem,
- select and apply a particular large language model to a particular problem,
- understand basic model evaluation methods.
Syllabus
  • 1. Seeking of the meaning: evolution of semantics.
  • 2. Structuralist semantics: logical representation, semantic relations, component analysis
  • 3. Word knowledge and world knowledge: semantic and lexical networks, ontologies.
  • 4. Semantic relations in existing data resources, inference.
  • 5. Formal languages for knowledge representation: RDF, OWL. Linked open data.
  • 6. Probabilistic models.
  • 7. Word embeddings. Pre-trained models.
  • 8. Transformers. Large language models. Generative models.
  • 9. Discourse analysis, anaphora resolution. Towards pragmatics.
  • 10. Introduction to model evaluation.
Literature
    recommended literature
  • GODDARD, Cliff. Semantic Analysis : a practical introduction. Oxford: Oxford University Press, 1998, xv, 411 s. ISBN 0-19-870017-2. info
Teaching methods
Lectures, and learning materials in the IS (presentations, videos in Czech). Hands-on seminar, in form of Jupyter Notebook in Colab (no installed software needed).
Assessment methods
Presentation of a scientific article or a current topic related to the field (student's choice).
Language of instruction
Czech
Further comments (probably available only in Czech)
Study Materials
The course is also listed under the following terms Autumn 2013, Spring 2014, Autumn 2014, Spring 2015, Spring 2016, Spring 2017, Spring 2018, Spring 2019, Spring 2021, Spring 2022, Spring 2023, Spring 2025.
  • Enrolment Statistics (recent)
  • Permalink: https://is.muni.cz/course/phil/spring2024/PLIN037