Language and linguistics today: Corpus linguistics with python programming language 2510-f1ENG2W-LLT-CLP

https://moodle.umk.pl/course/view.php?id=3833

The aim of the course is to introduce students to the use of programming in corpus linguistics. The course will involve familiarising students with the syntax and semantics of Python and its application in analysing large linguistic datasets.

The course puts a strong emphasis on obtaining programming skills with a view to applying them in future academic research. During the course, students will acquire skills related to manipulating data structures, processing raw text files to obtain informative output, defining functions and other skills that aid quantitative linguistic analysis.

Content distribution:

- Introduction
- Corpus linguistics, computational linguistics and natural language processing
- Introducing Python: Python among other programming languages, basic concepts
- Basic data structures in Python
- Operators, expressions, control flow, loops
- Working with text files, regular expressions
- Tokenisation, part-of-speech tagging
- Phrase-structure and dependency parsing
- Text classification: topic modelling and sentiment analysis

W cyklu 2022/23Z:

As in part A

Całkowity nakład pracy studenta

Participation in the seminar (30 hrs - 1 ECTS)

Efekty uczenia się - wiedza

The student can define basic concepts and issues related to corpus linguistics (K_W03).

Efekty uczenia się - umiejętności

The student can process text files to obtain relevant output (K_U01). The student can differentiate between corpus linguistics and natural language processing and can use basic concepts from these disciplines (K_U06) The student can search for relevant information in order to solve common problems in computational linguistics, corpus linguistics and natural language processing (K_U10)

Efekty uczenia się - kompetencje społeczne

The student understands the constant need to acquire new skills in the area of computational linguistics (K_K01)

Metody dydaktyczne podające

- pogadanka
- opis

Metody dydaktyczne poszukujące

- seminaryjna
- klasyczna metoda problemowa
- projektu
- doświadczeń

Wymagania wstępne

- interest in linguistics - basic computer skills

Koordynatorzy przedmiotu

Marek Placiński

Kryteria oceniania

- active participation in the seminar (20 %) [K_U01, K_K01]
- end-of-the semester project (80 %) [K_W03, K_U01, K_U06, K_U10]

Evaluation criteria:

fail – 0 – 59%
satisfactory - 60 – 69%
satisfactory plus - 70 – 75%
good - 76 – 85%
good plus - 86 – 90%
very good - 91 – 100%

Literatura

Bird, S., Klein, E. & E. Loper. 2009. "Natural Language Processing with Python", available here: https://www.nltk.org/book/

Jurafsky, D. & J.H. Martin. "Speech and Language Processing", available here: https://web.stanford.edu/~jurafsky/slp3/

W cyklu 2022/23Z:

As in part A

Uwagi

W cyklu 2022/23Z:

As in part A

Więcej informacji

Dodatkowe informacje (np. o kalendarzu rejestracji, prowadzących zajęcia, lokalizacji i terminach zajęć) mogą być dostępne w serwisie USOSweb:

Strona przedmiotu 2510-f1ENG2W-LLT-CLP w USOSweb