General information
| Course name | Seminar: 10.33.348 Building Up Linguistic Data Analysis Techniques in Python |
| Subtitle | |
| Course number | 10.33.348 |
| Semester | SoSe2026 |
| Current number of participants | 13 |
| expected number of participants | 15 |
| Home institute | Institute of Dutch Studies |
| Courses type | Seminar in category Teaching |
| First date | Monday, 13.04.26, 10:00 - 12:00 o'clock V03 0-M018 |
| Type/Form | Ü |
| Pre-requisites |
Have you learned some Python basics already, but are wondering how to put them to use with real linguistic data? Whether you are dealing with annotated corpora, lexical databases, or acoustic measurements, this course will help you work with them more effectively! Starting from everyday Python knowledge, the course guides you through practical techniques for managing and analyzing linguistic datasets. You will first tackle advanced tabular data operations: cleaning, filtering, reshaping, and integrating datasets, before moving into numerical computing, where you will use array-based methods to compute distances and similarities, extract features, and represent linguistic units in vector form. Potential topics include (but are not limited to): - Cleaning and reshaping corpus-derived datasets - Representing linguistic units as numerical arrays - Applying vectorized operations to compute distances, similarities, and transformations - Using linear algebra routines relevant to linguistic modelling By the end of the course, you will be able to build reproducible data-processing workflows and apply numerical methods to a wide range of linguistic research questions. |
| Performance record |
Each session will include hands-on practice exercises and a short assignment. The grading structure is as follows: Requirements for 3 CPs: - Script submission after each session (50%) - Short assignments (50%) Requirements for 6 CPs: - Script submission after each session (30%) - Short assignments (30%) - A final assignment at the end of the course (40%) The final assignment involves preprocessing and analysis of a linguistic dataset using Python. You will receive a dataset, perform necessary preprocessing, conduct a small analysis, and summarize the results. The submission deadline is currently planned for the end of August. You can also participate in the course without pursuing grades or CPs. [IMPORTANT]: You must bring your own laptop with internet access, with Python already installed and functioning. Please make sure Python is ready to use before the first session. You may use Python through any interface you prefer, such as PyCharm, Jupyter Notebook/Lab, or VS Code. I am looking forward to seeing you in the course! |
| Lehrsprache | deutsch |
| ECTS points | 3 |