| Module: | Natural Language Processing |
| Module numbers: | 41.5086 [PVL 41.5087; Module 41.50860] |
| Language: | english |
| Study programme: | Dualer Master 2021 - Katalog AS: Anwendungs- und systemorientierte Module
Master 2021 - Katalog AS: Anwendungs- und systemorientierte Module
Dualer Master 2013 - Katalog AS: Anwendungs- und systemorientierte Module
Master 2013 - Katalog AS: Anwendungs- und systemorientierte Module
MN Data Science 2016 - Katalog DS-I: Data Science - Informatik |
| Type of course: | V+P = Lecture+Practical |
| Weekly hours: | 2+2 |
| Credit Points: | 6 |
| Exam: | written exam |
| Registering for exam | explicitly and independent of booking |
| PVL (e.g. Practical): | graded (Group project from one of the subfields of NLP - incl. Documentation; graded individual assignments) |
| PVL percentage: | 50% |
| Frequency of offering: | each year (lastly in SS 2022) |
| Required knowledge: | Basic concepts and ways of thinking in the field of artificial intelligence (Bachelor level) |
| Learning objectives: | The students will
- understand the relevance of Natural Language Processing (NLP) as a sub-field of Artificial Intelligence
- understand the complexity of NLP applications, and on the basis of a detailed analysis, point at the problem and become sensible w.r.t a solution
- get familiar with NLP tools and apply them
- acquire knowledge in the subfields of NLP: morphology, Tokenization, Tagging, electronic dictionaries, Syntax, Semantics, Machine Translation (rule-based and statistical), Text Mining, and Speech Recognition
- understand the connection between NLP and Computational Linguistics, i.e. different views on the same field
- become sensible to problems in the NLP field - focusing on disambiguation on different levels (word-, sentence-, text-, web)
- have acquired theoretical skills across the entire field of NLP and will be able to apply them
- be able to analyze an NLP problem, design & implement a prototypical solution and document the work
|
| Content: | This course will cover the following aspects of Natural Language Processing (NLP): tokenization, tagging, parsing, morphology, electronic dictionaries, problems in homonyms and disambiguation in general, machine translation, syntax, grammatical theories, CD structures, RTNs, ATNs, electronic grammar checking, statistical language processing: Bayes Rules and Hidden Markov Models. |
| Literature: | - Jurafsky, Daniel. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall, 2008.
- Manning/Schütze. Foundations of Statistical Language Processing. Foundations of Statistical Natural Language Processing. MIT Press. 1999.
- Pierre Nugues. An Introduction to Language Processing with Perl and Prolog: An Outline of Theories, Implementation and Application with Special Consideration of English, French, and German (Cognitive Technologies). Springer Berlin Heidelberg, 2009.
|
| Lecture style / Teaching aids: | Seminaristic Lecture; Videos of the Lectures; Slides |
| Responsibility: | Bettina Harriehausen |
| Released: | WS 2021/2022 |
| Offered in SS 22: | LN: Harriehausen |
| Professional competencies: | - formal, algorithmic, mathematical competencies: medium
- analytical, design and implementation competencies: medium
- technological competencies: medium
- capability for scientific work: high
|
| Interdisciplinary competencies: | - project related competencies: medium
- interdisciplinary expertise: basic technical and natural scientific competence
|