Infopaket

Multi-semester discipline Programming Technologies within Linguistics. Part 3, 4

ДВС 1.06

Вибіркова дисципліна для ОП

First

2021/2022

8 Semester

8

PLO 24. To know and to implement fundamental conceptions, paradigms, and the main functioning principles of language, instrumental and computing means of software engineering. PLO 25. To conduct a pre-project inspection of a linguistic branch and system analysis of the linguistic object of software designing. PLO 26. To be able to choose and use methodology for creating software in accordance with a linguistic task. PLO 28. To be able to develop a human-machine interface. PLO 30. To select the programming languages and technologies for solving tasks in developing and running software for automatic linguistic systems. PLO 31. To know and be able to use information technologies for data processing, storage, and transfer. PLO 32. To know approaches for software assessment and quality assurance.

Full-time form

1) Having basic programming skills; 2) understanding the main tasks of computational linguistics.

The educational discipline is devoted to the study of issues necessary for solving tasks of computer linguistics, in particular, the creation of graphic (window) and console projects for linguistic applications; modeling of morphology, inflection, and syntax of natural languages; interactions with databases of linguistic information; implementation of electronic lexicographic and educational systems for natural languages. To implement practical tasks in the discipline, the C# and Python programming languages, Microsoft Visual Studio and IntelliJ PyCharm visual software development environments, the SQLite database management system, etc. are studied.

1. Bird S. Natural Language Processing with Python [Електрон. ресурс] / Steven Bird, Ewan Klein, and Edward Loper. – 2020. – URL : https://www.nltk.org/book. – Дата звернення: 12.10.2020. 2. Lane H., Howard C., Hapke H. M. Natural Language Processing in Action: Understanding, analyzing, and generating text with Python. – Shelter Island : Manning, 2019. – 544 p. 3. Joshi P. Artificial Intelligence with Python. – Birmingham - Mumbai : Packt, 2017. – 446 p. 4. Deitel P., Deitel H. Python for Programmers. – London : Pearson Education, 2019. – 640 p. 5. Bengfort B., Bilbro R., Ojeda T. Applied Text Analysis with Python: Enabling Language-Aware Data Products with Machine Learning. – Beijing; Boston; Farnham; Sebastopol; Tokyo : O'Reilly, 2018. – 332 p.

Lectures, laboratory classes, independent work. Types of work: Laboratory work, modular control test.

After completing the work, students upload the report and code (if necessary) to the Moodle system. After that, students defend their work. Laboratory works are evaluated as follows: for each work, one can get from 9 to 15 points. In general, students can get from 27 to 45 points for all laboratory work. The deadlines for the work are specified in the Moodle system. During the semester, after the completion of all topics of the content module, a module control test (MCT 2) is conducted, which is evaluated from 9 to 15 points. In total, based on the results of laboratory work and writing MCT 2, a student can receive from 45 to 60 points. Final evaluation in the form of an exam: 40 points (40%). A student is not admitted to the exam if he scored less than 36 points during the semester. In order to be admitted to the exam, a student must pass a module test for a positive assessment. The exam score cannot be less than 24 points to obtain an overall passing grade for the course.

Ukrainіаn, English