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 the contemporary methods to address them. The course will cover tasks such as language modeling and word/sentence representations, text classification, sequence tagging for finding parts of speech or morphological features, information extraction such as named entity recognition, finding the important structural parts of a sentence as well as some higher level tasks such as machine translation.
During recent years, the NLP field has more and more started to use deep neural models. Thus, in this course we will look at various deep neural models that are nowadays commonly used for NLP: recurrent networks for modeling sequential data, convolutional networks for text classification, static and contextual word embeddings, attention mechanism for finding alignment between different inputs or inputs and outputs.
According to the University guidelines, the lectures and practicums will be virtual until the end of the semester.
- Lectures: Wednesdays at 10:15
- Delta building (Narva mnt 18), room 1008
- Lecture zoom
- Labs: Tuesdays at 16:15
- Delta building (Narva mnt 18), room 2048
- Labs zoom
- Lecturer: Kairit Sirts (email@example.com)
- Virtual office hours: Wednesdays 11:45-12:15, in the Lecture zoom room
- Main TA: Claudia Kittask (firstname.lastname@example.org)
- Backup TA: Kirill Milintsevich (email@example.com)
|Reading tests||20 points||10 reading tests, max 2 points each|
|Reading questions||5 points||1 question per min 5 reading topics, max 1 points each|
|Homeworks||42+6 points||6 practical homeworks, max 7 points each + max 1 point per extra task|
- Deadlines for homeworks and project milestones are on Tuesdays at 23:59.
- Deadlines for reading tests and questions are on Wednesdays at 23:59.
All deadlines are strict!
In order to pass the course, you have to:
- Obtain half of the points from each assessment type:
- 10 from reading tests,
- 2 from creating reading questions,
- 21 from homeworks,
- 18 from the project.
- Submit at least 5 homeworks out of 7 (the second homework comes in two parts).
- Each of the submitted homeworks must be worth of at least 1 point.
- Completing the 2nd homework part I is mandatory!
- Submit all six project milestones.
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.