LTAT.01.001 Natural language processing
This course aims to provide an overview of the main tasks in the field of natural language processing and to introduce contemporary methods to address them. The course will cover tasks such as language modeling and word/sentence representations, text classification, sequence labeling for tagging words or for extracting information such as named entities, finding the important structural parts of a sentence as well as some higher level tasks such as machine translation or question answering.
Currently, the NLP field is dominated by the use of artificial neural networks. Thus, in this course we will look at various deep neural models that are nowadays commonly used for NLP: feedforward neural networks for text classification and learning word representations (embeddings), recurrent networks for modeling sequential data and attention-based transformers for training powerful large language models.
Course info
- Lectures and seminars: Wednesdays at 10:15
- Delta building (Narva mnt 18), room 1019
- Practicums: Wednesdays at 14:15
- Delta building (Narva mnt 18), room 1019
- Lecturer: Kairit Sirts (kairit.sirts@ut.ee)
- TA: Emil Kalbaliyev (emil.kalbaliyev@ut.ee)
- TA: Aleksei Dorkin (aleksei.dorkin@ut.ee)
The lectures and practice sessions will be recorded. The recordings will be made available via Moodle.
Join the slack using your university email.
Assessment
| Type | Points | Comment |
|---|---|---|
| Practical homeworks | 40 points | 4 practical homeworks, max 10 points each |
| Theory test | 20 points | 05.04.2023 during lecture class |
| Project | 30 points | project code and report, peer feedback, project presentation |
| Seminar presentation | 10 points | Based on an article on a given topic |
| Additional points | max 5 points | There will be opportunities to get extra points |
| Total | 105 points |
How to pass the course?
In order to pass the course, you have to obtain at least 51 points from any course activities (homeworks, theory test, project, seminar presentation). The requirement is strictly at least 51 points (and not 50 or 50.99).
None of the course activities are compulsory. However, most course activities can only be done on the scheduled times and cannot be compensated later. Thus, we advise you to consider carefully in case you decide to skip any of the activities.
Plagiarism
The course activities include both individual and group work. Homeworks and theory test are strictly individual work. You are allowed to discuss individual assignments in groups but your solution must be your own.
We will check the individual work for plagiarism. If we have a suspicion then we will inform you and allow you to clarify the issues. If you are caught first time in cheating or copying your coursemate's work then you will receive no points for that individual work. If you are caught the second time then you will get no further points from the course which may result in receiving a low grade or failing the course. If you feel that you have been treated unfairly then you can contact the Dean's office.
All written coursework (the theory test and the project report) must be written by you. No AI generated content is allowed. We will check all written submissions for AI generation with the latest tools and if your work is flagged as AI generated then it will be treated the same as plagiarism.
Prerequisites
This course assumes knowledge from various areas. In Study Information System, the required prerequisite course is Machine Learning (MTAT.03.227) and the recommended prerequisite courses are Language Technology (MTAT.06.045) and Artificial Intelligence I (MTAT.06.008). In practice, we also assume the basic knowledge of higher math (calculus, linear algebra, probabilities) and computer programming (python). If you lack some of the required knowledge then it is your responsibility to acquire it at the level necessary for advancing on this course. We can help to find suitable materials for obtaining the necessary background.