• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
Master 2023/2024

Programming in Python

Type: Compulsory course (Applied Linguistics and Text Analytics)
Area of studies: Fundamental and Applied Linguistics
Delivered by: School of Fundamental and Applied Linguistics
When: 1 year, 1, 2 module
Mode of studies: distance learning
Online hours: 66
Open to: students of one campus
Master’s programme: Прикладная лингвистика и текстовая аналитика
Language: English
ECTS credits: 6
Contact hours: 56

Course Syllabus

Abstract

The course consists of sections devoted to the study of text data processing methods. As part of the training, it is supposed to master the methods of preprocessing text data, algorithms for solving classical problems based on classical machine learning and deep neural networks.
Learning Objectives

Learning Objectives

  • Study of methods and approaches for automatic processing of text data using the theory of classical machine learning and deep neural networks.
Expected Learning Outcomes

Expected Learning Outcomes

  • A student understands the basics of word-to-vector representations, is familiar with the main approaches of text classification, writes examples of programs in Python
  • A student is familiar with basic methods of preprocessing and feature extraction applied to the TA
  • A student understands the basics of sequence-to-sequencerepresentations, is familiar with such terms as Sequence Markup. Seq2seq, MT, attention, transformer, writes examples of programs in Python
  • A student is familiar with the some pre-trained language models, writes an examples of programs in Python
  • A student understands the basics of thematic modeling, is familiar with the main approaches of text summarization and simplification, writes the examples of programs in Python
  • A student is familiar with the main automatic methods for analyzing the sentiment of documents in general and by aspects, writes the examples of programs in Python
Course Contents

Course Contents

  • Introduction
  • Part 1
  • Part 2
  • Part 3
  • Part 4
  • Part 5
Assessment Elements

Assessment Elements

  • non-blocking Homework
  • non-blocking Homework
  • non-blocking Test
Interim Assessment

Interim Assessment

  • 2023/2024 2nd module
    0.3 * Homework + 0.3 * Homework + 0.4 * Test
Bibliography

Bibliography

Recommended Core Bibliography

  • Прикладной анализ текстовых данных на Python : машинное обучение и создание приложений обработки естественного языка, Бенгфорт, Б., 2020

Recommended Additional Bibliography

  • Learning Python : [covers Python 2.5], Lutz, M., 2008
  • Python 3, Прохоренок, Н. А., 2016
  • Python и анализ данных, Маккинли, У., 2015
  • Python. Самое необходимое, Прохоренок, Н. А., 2015

Authors

  • Balakina Iuliia Vladimirovna
  • KARATETSKAYA EFROSINIYA YUREVNA