Course syllabus

DAT450/DIT247 Machine Learning for Natural Language Processing, 2024, period 2.

For questions about the course, please get in touch with Richard (richajo@chalmers.se).

Department of Computer Science and Engineering (CSE), Gothenburg University | Chalmers

Course content

The course gives an introduction to machine learning models and architectures used in modern natural language processing (NLP) systems.

Official syllabus:

• GU syllabus

• Chalmers syllabus

Passing the course

The examination includes five mandatory programming assignments, four mandatory sets of reflection questions, and one mandatory self-defined project that requires the submission of a written report and an oral presentation. To pass the course and get the grade Pass (3), all assignments, reflection question sets, and the final project must be passed. The programming assignments and the project are conducted in a group of 2-4 students, while the reflection questions are solved individually.

Each submitted programming assignment, as well as the project submission, will be checked for whether it reaches a level of a minimal pass. If you submit a solution to a programming assignment or the project before the deadline that does not meet the requirements for a Pass grade, you will get some feedback and be asked to correct the most important errors within a stipulated period of time.

A submission to a set of reflection questions is passed if it answers at least 25% of the questions correctly. Students who fail these submissions may ask the examiner for a compensation assignment, which will be decided by the examiner on an individual basis (based on the errors in the first submission).

If you miss the deadline (or the resubmission deadline), or if the examiner believes that the solution was not an honest attempt to solve the assignment, the solution will get the grade of Fail (U). If you have received the U grade for some submitted assignment, you can submit a new attempt during next year's course. In exceptional circumstances, individual deadline extensions may be allowed if a student approaches the examiner before the submission deadline.

Grading system

If you pass the course according to the criteria above, you will receive a grade on a numerical scale (3–5). The grade is based on the following parts:

• Reflection questions: each set of reflection questions can give up to 8 points. There are four such sets of questions.
• Programming assignment 3: this assignment requires people to submit a short report that will be graded, giving up to 8 points.
• Classroom participation bonus: 8 of the classroom sessions give 0.5 bonus points, for a total of up to 4 points.
• Project: up to 30 points, mainly based on the quality of the technical report.

Once a submission has passed, we do not allow re-submission of any assignment in order to improve scores.

The final grade is computed from the sum of scores for all the parts listed above, using the following thresholds:

59-74 (at least 80% of the maximal): 5

44-58.9 (at least 60% of the maximal): 4

up to 39.9: 3

Working in groups

Most assignments in the course are group assignments, and for these assignments it is compulsory to work in a group. If you have a very strong reason for working alone (e.g. related to your health or some other special circumstances), you can ask the examiner for an exemption. In this case, you need to include a statement in your submission that you got an exemption from the requirement to work in a group. Individual submissions that do not include this statement will not be graded.

General Rules and Policies

Please be aware of the general rules at the university regarding disciplinary matters.

• GU rules
• Chalmers rules

In particular, for this course we stress that

• You are responsible for your answers.
• You must write your submissions on your own, using your own words, and expressing them in the way you understood them yourself.
• It is prohibited to copy (with or without modifications) from each other, from sources such as books, articles, or web pages. If you rely on an external source for some information, please include a citation in your answer.
• For assignments that require you to submit written text (in particular, the final project report), we allow students to use grammar-improving tools such as Grammarly. Similarly, we allow outputs by large language models (such as ChatGPT, Claude) if they are used for the purpose of improving spelling, grammar, or writing style. However, using large language models to generate substantive content is not allowed in submissions: in this respect, we regard LLM-generated output as plagiarized and functionally equivalent to copying from any other source. The examiners reserve the right to use tools that detect LLM-generated text.