Deep learning for natural language processing

1.

Subject title

Deep learning for natural language processing

Длабоко учење за обработка на природните јазици

2.

Code

m23_w_028

3.

Study program

Bioinformatics, Security, Cryptography and Coding, Cloud Computing, Еducation with ICT, Eco-informatics, Inteligent Systems, Internet Technologies and cyber security, Computer Science, Statistics and Data Analytics, Software for embedded systems, Software Engineering, Cloud Computing, Bioinformatics, Security, Cryptography and Coding, Statistics and Data Analytics, Software Engineering, Data science in computer science and engineering, IT management, IT management,

4.

Organizer of the study program (unit, institute, department, division)

Faculty of Information Sciences and Computer Engineering

5.

Study cycle (first, second, third)

Втор циклус

6.

Academic year / semester

5 / Зимски

7. Number of ECTS credits

6.0

8.

Instructor

проф. д-р Соња Гиевска

9.

Prerequisites for enrollment

10.

Subject goals and competencies:

The purpose of the subject is to get acquainted with the modern deep learning techniques for understanding natural languages ??and generating text. Upon completion of the subject, the student will be capable of selecting and applying appropriate deep neuronal architecture for problems in the field.

11.

Subject content:

Some of the topics are committed to introducing the student to the challenges and achievements in the field of natural languages ??processing: modeling natural languages. Affective analysis. Detection of antisocial phenomena on the web (eg abusive speech, false news, hate speech and prejudice). Machine translation. Generating text by applying documents, conversational-dialogue agents, answers to questions and changing the style of text. Analysis and interpretation of text understanding and generation systems. Review of ethical and moral absects in natural languages ??processing systems. Modern-deep learning techniques will be used to solve problems in the field: deep neuronal networks with attention, generative opposing networks, graphs-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-non-current networking networking and learning learning.

12.

Learning methods:

Предавања поддржани со презентации преку слајдови, интерактивни предавања, вежби (користење на опрема и софтверски пакети), тимска работа, студија на случај, поканети гости предавачи, самостојна изработка и одбрана на проектна задача и семинарска работа, учење во електронско опкружување (форуми, консултации).

13.

Total available time fund

6.0 ECTS x 30 hours = 180 hours

14.

Time distribution

60 + 0 + 45 + 45 + 30 = 180 hours

15.

Forms of teaching activities

15.1.

Lectures - theoretical teaching

60 hours

15.2.

Exercises (laboratory, classroom), seminars, team work

0 hours

16.

Other forms of activities

16.1.

Project tasks

45 hours

16.2.

Independent tasks

45 hours

16.3.

Homework

30 hours

17.

Grading method

17.1.

Tests

15 points

17.2.

Seminar work / project (presentation: written and oral)

45 points

17.3.

Activities and learning

15 points

17.4.

Final exam

0 points

18.

Grading criteria (points / grade)

up to 50 points

5 (five) (F)

from 51 to 60 points

6 (six) (E)

from 61 to 70 points

7 (seven) (D)

from 71 to 80 points

8 (eight) (C)

from 81 to 90 points

9 (nine) (B)

from 91 to 100 points

10 (ten) (A)

19.

Condition for signature and taking final exam

Реализирани активности 15.1 до 15.2, и 16.1 до 16.3

20.

Language of instruction

Македонск и англиски

21.

Quality assurance method

Механизми на интерна евалуација и анкети

22.

Literature

22.1.

Mandatory literature

22.2.

Additional literature