Course in Advanced Natural Language Processing
General Information
| Lecturer | Dr. Thomas Eckart |
| Tutors | Erik Körner, Felix Helfer, Dr. Thomas Eckart |
| Workload | 2 SWS Lecture, 1 SWS Tutorial |
| Lecture | Monday, 11:15 - 12:45, starting 17.10.2022, SG 3-10 |
| Tutorial | Monday, 13:15 - 14:45, starting 7.11.2022, SG 3-10 |
| Contact | via Email |
| Exam | Written Exam; Date: 13.02.2023 11:00 - 12:00 Room: S 126 |
| Post-exam review | Date: 11.04.2023 09:00 - 13:00 Room: P 825 |
| 2nd Exam | Written Exam; Date: 26.04.2023 09:00 - 10:00 Room: P 702 |
Lecturenotes (accessible within Leipzig university network)
- Lecture 1: Organisation, Overview, Literature, Introduction NLP & Wortschatz Leipzig
- Lecture 2: Linguistic Processing Pipelines: Examples, Text, Sources, Language Identification
- Lecture 3: Linguistic Processing Pipelines: Text Segmentation, Pattern-based Cleaning, Influence of Preprocessing
- Lecture 4: Linguistic Processing Pipelines: Queries, Data structures
- Lecture 5: Linguistic Processing Pipelines: Stemming, POS-Tagging
- Lecture 6: Sequence Labeling (POS/NER)
- Due to illness, the lecture on 05.12.2022 is canceled. The exercise/tutorial on the same day will take place at the usual time (13:15).
- Lecture 7: Language Statistics, Corpus Comparison, Supplementary Material: Log-likelihood-ratio & TF/IDF
- Lecture 8: Distributional semantics, Co-occurrences
- Lecture 9: Vector Space Model, Vector Semantics
- Lecture 10: Lexical Disambiguation
- Lecture 11 & 12: NLP in Research Data Management
- Summary & Exam preparation
Tutorialnotes (accessible within Leipzig university network)
- Tutorial 1: Preprocessing tasks (Language Identification, Sentence Segmentation, Tokenization)
- Presentation 'Clickbait Spoiling at SemEval 2023'
- Tutorial 2: Data structures, Stemming, POS-Tagging
- Paper 'CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models'
- Tutorial 3: Hidden Markov Models, SentiWS
- Tutorial 4: Trans-Co-Occurrences, Authorship Analysis
- Tutorial 5: Co-Occurrences, Vector Space Models
- Tutorial 6: Sentiment Lexicon, Web Annotation Frameworks
- Jupyter Notebook: Creating a Sentiment Lexicon