Infopaket

Machine Translation

ННД 08.09

Обов’язкова дисципліна для ОП

First

2022/2023

6 Semester

2

PLO 15. To conduct linguistic analysis (phonetic, morphemic, syntax, word formation, morphological, semantic), literary criticism, and translation studies analysis of texts of different genres and styles, as well as computer modeling of analysis and synthesis of linguistic objects and phenomena. PLO 16. To know and understand the major notions, theories, and conceptions of structural, mathematical, and computational linguistics, and to be able to use them in professional activity. PLO 17. To collect, analyze, systematize (to create system-oriented and text-oriented linguistic database) and interpret language facts and speech, and to use them for solving complicated tasks and problems of automatic linguistic analysis in specialized spheres of professional and/or learning activity. PLO: 21, 25.

Full-time form

1) Successful mastering of complex disciplines: Theoretical Linguistics, Applied Linguistics, Informatics, Mathematical foundations of the specialty; 2) Knowledge of the theoretical foundations of general linguistics, mathematical and computer linguistics, computer science, and programming; 3) Mastery of linguistic analysis techniques at all language levels; basics of corpus technologies, skills of mathematical and computer modeling of linguistic phenomena; mathematical basics of computer technology; 4) The ability to carry out corpus markup at different levels, to use a programming language to solve problems of input, output, and processing of text information.

Within the scope of the discipline, different formulations of the task of translation from one language to another, the main directions of automatic translation, their development, problems, and prerequisites of the formation of modern approaches, and the connection of machine translation with other tasks of computer linguistics are considered. Modern machine translation systems are studied and compared, as well as the main problems of this field, ways to solve them, and the future development of automatic translators are analyzed. Students will test modern machine translation systems and get acquainted with their general architecture in practical classes within the course. Means and tools for natural language processing, as well as methods for creating parallel corpora, will be studied. Students will also learn to evaluate the quality of machine translation using modern methods and metrics of experts and automatic evaluation of translation results.

Dabre, R., Chu, C., & Kunchukuttan, A. (2020). A survey of multilingual neural machine translation. ACM Computing Surveys (CSUR), 53(5), 1-38. Freitag, M., Foster, G., Grangier, D., Ratnakar, V., Tan, Q., & Macherey, W. (2021). Experts, errors, and context: A large-scale study of human evaluation for machine translation. Transactions of the Association for Computational Linguistics, 9, 1460-1474. Hutchins, W. J. (1995). Machine translation: A brief history. In Concise history of the language sciences (pp. 431-445). Pergamon. Jurafsky Daniel, Martin James H. Speech and Language Processing (3rd ed. draft). 2021. URL: https://web.stanford.edu/~jurafsky/slp3/ Kenny, D. (Ed.). (2022). Machine translation for everyone. BoD–Books on Demand.

Lectures, seminars, and laboratory classes, independent work. Types of work: Answer at the seminar session. Lab. Report-analysis of scientific literature. Tests.

During the semester, evaluation is carried out in accordance with the types of work (response in a seminar class, laboratory work, report-analysis of scientific literature, tests). The credit is given based on the results of the student's work throughout the entire semester and does not include additional assessment measures. Students who scored the minimum positive number of points - 60, receive - "Passed". Students who did not score the minimum positive number of points - 60, receive - "Failed".

Ukrainіаn