This is the course page for the summer semester 2018 edition of the course statistical natural language processing (NLP) at the Department of Linguistics, University of Tübingen.
Natural language processing is an important part of areas or disciplines that are concerned with language and computation including (computational) linguistics, artificial intelligence and computer science. NLP is crucial both for building practical applications and answering research questions in many areas of research.
This course is an undergraduate introduction to natural language processing. The aim of this course is to expose students to a large variety of topics in NLP. Broadly the topics of the course include:
- Machine learning techniques used in NLP, such as classification, sequence learning and unsupervised methods, with both ‘classical’ methods (e.g., logistic regression, naive Bayes) and (deep) neural networks.
- Statistical approaches to text processing, segmentation/tokenization, morphology, syntax and semantics.
- Common application areas of NLP, such as text classification, question answering, machine translation.
This is a practical, fast-paced, broad introduction to the field. Fluency in programming and ability to learn new programming languages and/or environments will be assumed.
The course is compulsory for the BA degree International Studies in Computational Linguistics. For other degree programs, please contact the instructor before signing up.
This year, we will use GitHub classroom for assignments. You need to obtain a GitHub account to receive and submit your assignments.
Further details can be found in the course syllabus.
Contact
- Instructor: Çağrı Çöltekin
<ccoltekin@sfs.uni-tuebingen.de>
Office hours: Wednesday 12:00 - 14:00 (Wilhelmstr. 19, room 1.09) - Tutor: Verena Blaschke <verena.blaschke@student.uni-tuebingen.de>