🎓 Learning Goals

Upon completion of the course, students will have acquired the skills necessary to apply Natural Language Processing (NLP) techniques to extract information from large language data sets and transform it into an understandable structure. Specific learning objectives to be fulfilled include:

Explain the theoretical structure of language using natural language data.
Implement NLP methods to analyze and transform natural language data.
Evaluate the suitability of natural language data sources for a data science problem.
Apply classical machine learning models and basic neural language models to language data.
Explain the limitations of NLP techniques based on insights from Cognitive Science.

📖 Coursework

📺 Video Lectures: Weekly video lectures discuss algorithms and theory at your own pace.
🧮 Exercises: You’re expected to be able to work out above algorithms on paper. The exercises allow your to practice this, and are to be completed after their respective lectures.
📚 Reading: Each video lecture and some of the labs will be accompanied by a set of recommended reading materials: book chapters, and articles are given per week.
🧑‍🏫 In-Person Lectures: The in-person lectures tie the video material to the lab sessions. These will provide context on how to use theory to tackle the task for the research paper.
💻 Lab Sessions: Notebooks serve as a guide to introduce tools for the interim assignment. You can ask questions about the notebooks, and research paper, during the sessions.

<aside> ⭐ Recordings (from last year): despite potential overlap with the in-person lectures, you may want to watch these. Last year’s interactive lectures were somewhat unstructured; a mix of answering questions from the discussion board, providing some additional contextual information, discussion points and practical examples (both in research and practice), and discussing example exam questions. May well prove useful.

</aside>

🖥️ Interim Assignment (40%)