| Session | Lecturer | Date | Chapter | Topic | Reading Assignment | Slides |
| 1
| WD
| 2/10/2017
| Theory
| Introduction to Computational Linguistics
| Jurafsky & Martin: Chapter 1
| SLIDES
|
| 2
| GDP
| 9/10/2017
| Theory
| Regular Expressions and Finite State Automata & Transducers
| Jurafsky & Martin: Chapter 2; Chapter 3
| SLIDES
|
| 3
| SS
| 16/10/2017
| Theory
| POS-tagging & Minimum Edit Distance
| Jurafsky & Martin: Chapter 3.11 & Chapter 5 (not 5.5, 5.8 and 5.9)
| SLIDES
|
| 4
| SS
| 23/10/2017
| Theory
| Syntactic Analysis & Parsing
| Jurafsky & Martin: Chapter 12 (not 12.7.2, 12.8); Chapter 13 (not 13.4.1, 13.4.2, 13.5.1)
| SLIDES
|
| 5
| GDP
| 30/10/2017
| Theory
| Probabilistic Methods
| Jurafsky & Martin: Chapter 4.1, 4.2 and 4.3; Chapter 5.5 and 5.9; Chapter 14.1, 14.3 and 14.4;
| SLIDES
|
| 6
| WD
| 6/11/2017
| Theory
| Lexical semantics and Distributed Representation
| Jurafsky & Martin: Chapter 19.1->19.4; Chapter 20.1->20.8; Chapters 17 and 18 (background reading); Chapter 15 in 3rd edition (background reading)
| SLIDES
|
| 7
| SS
| 13/11/2017
| Theory
| Semantic role labeling and sentence semantics
| Jurafsky & Martin: 3rd edition: Chapter 22.1->22.6;
| SLIDES
|
| 8
| WD
| 20/11/2017
| Theory
| Discourse
| Jurafsky & Martin: Chapter 21.1->21.8
| SLIDES
|
| 9
| SS
| 27/11/2017
| Practice
| Regular Expressions, Part-of-speech Tagging, FrameNet (EXERCISES)
|
|
| 10
| WD
| 4/12/2017
| Practice
| Lexical and Discourse semantics (EXERCISES-2 python, EXERCISES-2 pdf)
|
|
| 11
| WD/SS
| 11/12/2017
| Student presentations
Format: 20 minutes presentation + 10 minutes questions.
Evaluation: thoroughness of research (include as your last slide a list of consulted resources) and clarity of presentation
Send your topic as soon as possible to walter.daelemans@uantwerpen.be
|
| 12
| WD/SS
| 18/12/2017
|
| author profiling | Danguole Kotryna Kapkanaite |
| authorship attribution | |
| automatic essay grading | |
| automatic subtitling | |
| automatic summarization | |
| biomedical information extraction | |
| cross-language information retrieval | |
| culturomics | Wesley Hermans |
| deception detection | |
| dictation software | Elisabeth Cappon |
| dialogue systems, natural language interfaces, chatbots | Sander Hoeven |
| emotion detection in text | Leonie Vanstappen |
| grammar and style checking | |
| (open) information extraction | |
| language and complexity | |
| language technology for language teaching | Elisabeth Pleunis |
| language technology for people with limitations | |
| language technology in (serious) gaming | |
| machine translation | |
| named entity recognition | |
| ontology learning from text | |
| opinion / sentiment mining | Loic De Langhe |
| optical character recognition | |
| plagiarism detection | |
| question answering systems | |
| relation extraction | |
| social media text mining | |
| speech recognition | |
| speech synthesis | |
| spelling correction | |
| terminology learning | |
| text generation | |
| text analytics for cybersecurity | |
| word embeddings in NLP | |