Course in Natural Language Processing
General Information
| Lecturer | Dr. Thomas Eckart |
| Lab Advisors | Erik Körner / Felix Helfer |
| Workload | 2 SWS Lecture, 2 SWS Lab |
| Lecture | Tuesday, 13:15 - 14:45, HS 20, starting 2.4.2024 |
| Lab | Monday, 15:15 - 16:45, SG 2-14, A/B week, starting 15.4.2024 |
| Lecturenotes and lab material | see below |
| Exam | Wednesday 10.07.2024 10:30 - 11:30 Room: HS 7 |
| Post-exam review 1 | Monday 12.08.2024 12:30 - 14:00 Room: P 825 |
| Post-exam review 2 | Tuesday 01.10.2024 10:00 - 10:30 Room: P 825 |
| 2nd Exam | Monday 04.11.2024 10:30 - 11:30 Room: S 420 |
| Post-exam review - 2nd Exam | Tuesday 26.11.2024 10:00 - 10:30 Room: P 825 |
Lecturenotes
- Lecture 1: Organisation, Intro
- Lecture 2: Linguistic Levels & Terminology
- (Hint Masterstudiengang Medizininformatik)
- Lecture 3: Words, Preprocessing, Morphology
- Excursus: Byte-Pair Encoding tokenization, WordPiece tokenization
- Lecture 4: Word Classes
- Excursus: RDRPOSTagger
- Lecture 5: Intro Syntax / Syntax (Regular grammars)
- Excursus: Verb valency in German (E-VALBU)
- Lecture 6: Syntax (CFG/PCFG)
- Lecture 7: Corpus Linguistics / Corpora
- Lecture 8: Keyword extraction, Examples for corpus comparison (with corrected FCL example on slide 3, thanks again for the hint!)
- The lecture on May 28th has to be canceled due to illness.
- Lecture 9: Corpus Annotation, Text Representation
- Lecture 10: N-Gram Language Models
- Lecture 11: Sequence Labeling & HMMs
- Lecture 12: Semantics, Similarity Measures
- Lecture 13: Co-occurrences / Embeddings
Lab Sessions
Note: the notebooks of sessions 0-4 have been updated!
- Lab Session 0 (self-study): Introduction, Python Crashcourse (Data.zip), Installation instructions for Conda on Windows
- Lab Session 1 (B: 15.04.24, A: 22.04.24): L1-1_BasictextManipulationandNLTK.ipynb, L1-2_ComparingCorpora.ipynb, L1-3_SyntheticText.ipynb
- Lab Session 2 (B: 29.04.24, A: 06.05.24): L2_Morphology.ipynb
- Lab Session 3 (B: 27.05.24, A: 03.06.24): L3-1_Zipf.ipynb (Zipf Annotated Example, tagesschau_corpus.zip), L3-2_PSG.ipynb (PSG-QA-TREE-with-Indices.png)
- Lab Session 4 (B: 10.06.24, A: 17.06.24): L4-1_LanguageDetection.ipynb (tagesschau_corpus.zip), L4-2_TFIDF.ipynb, L4-3_KeywordExtraction.ipynb (keyword.zip, deu_news_2021_100K-sentences.txt), L4-4_Sentiment.pdf (L4-4_sentiment_lexicon.ipynb)
- Lab Session 5 (B: 24.06.24, A: 01.07.24): L5_HMMs.pdf, L5_ngram-LanguageModel.ipynb
