Contents
Linguistic information processing (natural language processing, computational linguistics) deals with the processing of natural language using computers. Well-known applications are machine translation systems or the extraction of information from large amounts of text. In this lecture, we deal with the theoretical and practical basics of language processing. In addition to dealing with the special features of language and linguistic description categories, we will take a quantitative look at language and the various possibilities for automatically recognizing and processing linguistic phenomena. Here we deal in particular with machine learning methods.
Course Work and Module Exam / Studienleistung und Modulprüfung
The coursework consists of the completion and submission of around five homework assignments, which are set during the semester. The module examination can be taken by writing a written exam.
Die Studienleistung besteht in der Bearbeitung und Abgabe von etwa fünf Hausaufgaben, die im Laufe des Semesters gestellt werden. Die Modulprüfung kann durch das Schreiben einer Klausur abgelegt werden.
Agenda
- 16.10. Introduction & overview over the field of computational linguistics (Folien)
- 23.10. Linguistics, linguistic levels (Folien)
- 30.10. Text corpora and manual annotation (Folien)
- 06.11. Quantitatively looking at language (Folien)
- 13.11. Predicting linguistic properties automatically (Folien)
- 20.11. Evaluation (cont.), Naive Bayes (Folien)
- 27.11. Naive Bayes, Decision trees (Folien)
- 04.12. Cancelled
- 11.12. Neural networks 1 (Folien)
- 18.12. Neural networks 2 (Folien, Code-Beispiele 1, 2, 3, 4)
- 08.01. Transformer architecture (Folien, s10-tokenizer.py, s10-get-bert-features.py, s10-unmasker.py, s10-fine-tune-text-classification.py)
- 15.01. Retrieval-augmented generation (RAG), skills & tools (Folien, s11-tool-calling.py)
- 22.01. In-Context-Learning/Prompting (Folien)
- Achtung, Sitzung fängt 20 Minuten später an
- 29.01. General exam questions
- 05.02. Exam