|
Instructors: Prof. Dr. Christian Biemann
Event type:
Lecture
Displayed in timetable as:
LT - VL
Hours per week:
2
Credits:
3,0
Language of instruction:
English
Min. | Max. participants:
- | 40
More information:
Language of instruction:
English, English materials.
Prerequisites for participation:
Required: No knowledge beyond general computer science on BA-level
Advantageous:
- introductory knowledge of machine learning
- introductory knowledge of statistics
Comments/contents:
This lecture gives detailed insights into statistical methods that are used in natural language processing systems. This includes supervised as well as unsupervised machine learning approaches in general, and methods for string and language processing in particular.
Key topics:
- Formal Languages and Automata
- Computational Morphology
- Sequence Tagging
- Topic Modelling
- Statistical Machine Translation
- Graph-Based Methods
- Distributional Semantics
- Word Senses and their Disambiguation
Learning objectives:
After attending this course, students are in a position to
- understand statistical methods for language processing in detail
- conduct methodological research in natural language processing
- analyze and evaluate the use of NLP in applications.
Didactic concept:
- Lecture and Practice class with homework assignments.
- Assignments involve pen-and-pencil exercises, small programming exercises and application of existing software.
Additional examination information:
- Written exam
- Language: English
- Prerequisite: 50% of homework assignments
|
