Course syllabus adopted 2026-02-18 by Head of Programme (or corresponding).
Overview
- Swedish nameMaskininlärning för språkteknologi
- CodeDAT450
- Credits7.5 Credits
- OwnerMPDSC
- Education cycleSecond-cycle
- Main field of studySoftware Engineering
- DepartmentCOMPUTER SCIENCE AND ENGINEERING
- GradingTH - Pass with distinction (5), Pass with credit (4), Pass (3), Fail
Course round 1
- Teaching language English
- Application code 87135
- Maximum participants50
- Minimum participants10
- Open for exchange studentsNo
Credit distribution
Module | Sp1 | Sp2 | Sp3 | Sp4 | Summer | Not Sp | Examination dates |
|---|---|---|---|---|---|---|---|
| 0120 Written and oral assignments 7.5 c Grading: TH | 7.5 c |
In programmes
- MPALG - Computer Science - Algorithms, Languages and Logic, Year 1 (elective)
- MPALG - Computer Science - Algorithms, Languages and Logic, Year 2 (elective)
- MPCAS - Complex Adaptive Systems, Year 1 (elective)
- MPCAS - Complex Adaptive Systems, Year 2 (elective)
- MPDSC - Data Science and AI, Year 1 (compulsory elective)
- MPDSC - Data Science and AI, Year 2 (elective)
- MPENM - Engineering Mathematics and Computational Science, Year 1 (elective)
- MPENM - Engineering Mathematics and Computational Science, Year 2 (elective)
- MPSOF - Software Engineering and Technology, Year 2 (elective)
Examiner
- Richard Johansson
- Full Professor, Data Science and AI, Computer Science and Engineering
Eligibility
General entry requirements for Master's level (second cycle)Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements
Specific entry requirements
English 6 (or by other approved means with the equivalent proficiency level)Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements
Course specific prerequisites
The course requires at least 7.5 credits of programming, 7.5 credits of probability theory or statistics, and a first course in machine learning, such as DAT340, TDA233, SSY340 or MVE440.Aim
The course gives an introduction to machine learning models and architectures used in modern natural language processing (NLP) systems.Learning outcomes (after completion of the course the student should be able to)
Knowledge and understanding:- describe the most common types of natural language processing tasks,
- describe the most common types of machine learning models and training algorithms used in modern natural language processing and large language models,
- explain how text data can be annotated for a natural language processing task where machine learning techniques are used.
- apply software libraries using machine learning for common natural language processing tasks,
- apply software libraries to load pre-trained large language models and to fine-tune these models,
- write the code to implement machine learning models for natural language processing and large language models,
- apply evaluation methods to assess the quality of natural language processing systems and large language models.
- discuss the advantages and limitations of different machine learning models with respect to a given task in natural language processing,
- reason about what type of data could be useful when training a model for a given natural language processing task,
- select the appropriate evaluation methodology for a natural language processing system and motivate this choice,
- reason about ethical questions pertaining to machine learning based natural language processing systems, such as stereotypes and under-representation.
Content
This is a technical course with a research angle that covers the technical solutions underlying modern NLP technologies and large language models.
The course covers the following broad areas:
- working practically with text data, including fundamental tasks such as tokenization;
- probabilistic models for text, such as topic models;
- overview of the most common types of NLP applications;
- machine learning architectures in NLP models, including word embeddings, recurrent neural networks, and Transformers;
- use of prompt-based large language models via APIs and locally;
- pre-training of representation models and large language models;
- fine-tuning models for instruction-following and reasoning.
Organisation
The teaching uses online lectures to watch before the class, active learning sessions where we review material from the corresponding lecture, and computer exercise sessions.
No activities with compulsory attendance.
Literature
Jurafsky & Martin, Speech and Language Processing.To be able to use the latest material, we recommend people to use the online version: https://web.stanford.edu/~jurafsky/slp3/
Examination including compulsory elements
The examination consists of hand-ins, some of which are solved individually and some in groups, a final group project requiring an oral presentation and the submission of a written report, and small tests used to evaluate what the students have learned from the activities in the course.The course examiner may assess individual students in other ways than what is stated above if there are special reasons for doing so, for example if a student has a decision from Chalmers about disability study support.