Patterns and Methods of Machine Translation (MTN)

Course: «Applied Linguistics (Translation Editing and Expert Linguistic Analysis)»

Structural unit: Educational and Scientific Institute of Philology

Title
Patterns and Methods of Machine Translation (MTN)
Code
ДВС.1.04
Module type
Вибіркова дисципліна для ОП
Educational cycle
Second
Year of study when the component is delivered
2021/2022
Semester/trimester when the component is delivered
3 Semester
Number of ECTS credits allocated
3
Learning outcomes
PLO 3. To implement modern methods and techniques, namely informational, in order to perform a successful and effective professional activity and guarantee the quality of research in an applied linguistics field. PLO 21.1. To apply professionally the knowledge of basic methods and principles of data extraction (Data Mining), an intellectual analysis of text data (Text Mining), organization and types of artificial neural networks, and types of machine learning tasks in the domain of Automatic natural language processing. PLO 22.1. To know and apply systematically the methods of analysis and applied (linguistic) industry modeling, determine the information needs and data collection to design software. PLO 25.1. To choose paradigms and programming languages to solve the Applied Linguistics problems, apply the system and specialized tools, component technologies (platforms), and integrated environments of software development. PLO 27.1
Form of study
Full-time form
Prerequisites and co-requisites
1. To know: the basics of the disciplines "Programming", "Discrete mathematics", "Probability theory", and "Construction and analysis of algorithms". 2. To be able to apply information technologies and programming languages ​​to solve applied problems and conduct scientific research. 3. To have basic skills in combining and analyzing algorithms, and programming in Python / Java / C++ languages. 4. To know English and English language terminology in the studied field.
Course content
The purpose of the discipline "Models and Methods of machine learning" is to obtain the necessary knowledge of modern information and intellectual technologies and the skills of their practical application for research and programming processes for solving complex problems of natural language text processing. As a result of studying the educational discipline, the student has: To know the main models, methods, and algorithms used to build machine learning systems. To be able to develop machine learning systems using modern technologies and programming languages ​​(specialized libraries for developing machine learning models, natural language processing, etc.).
Recommended or required reading and other learning resources/tools
1. Rish, Irina. (2001). «An empirical study of the naive Bayes classifier». IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence. 2. Карташов М. В. Імовірність, процеси, статистика — Київ, ВПЦ Київський університет, 2007. 3. Hosmer, David W., Stanley Lemeshow (2000). Applied Logistic Regression, 2nd ed.. New York; Chichester, 4. Harremoës P. and Topsøe F., 2001, Maximum Entropy Fundamentals, Entropy, 3(3), 191—226. 5. Nello Cristianini, John Shawe-Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. — Cambridge University Press, 2000. 6. Lawrence Rabiner. A tutorial on Hidden Markov Models and selected applications in speech recognition. Proceedings of the IEEE 77 (2): 257–286. 7. Lafferty, J., McCallum, A., Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proc. 18th International Conf. on Machine Learning. Morgan Kaufmann. с. 282–289.
Planned learning activities and teaching methods
Lectures, practical classes, independent work.
Assessment methods and criteria
Student evaluation forms: - semester assessment: 1. Control test 1: 7 points / 5 points. 2. Control test 2: 8 points / 5 points. 3. Laboratory work 1 (project): 15 points / 10 points. 4. Laboratory work 2 (project): 15 points / 10 points. 5. Laboratory work 3 (project): 15 points / 10 points. 6. Final test: 40 points / 20 points Types of tasks for the final test: 8 tests and 6 tasks in written form. The discipline ends with a credit. The final number of points for the discipline (maximum 100 points) is defined as the sum of points for systematic work during the semester, taking into account the final test.
Language of instruction
Ukrainian, English

Lecturers

This discipline is taught by the following teachers

Oleksandr O Marchenko
Mathematical Informatics
Faculty of Computer Science and Cybernetics

Departments

The following departments are involved in teaching the above discipline

Mathematical Informatics
Faculty of Computer Science and Cybernetics