Natural Language Processing (CUGS Core)2018VT
|
|
Course plan
Aim
Natural Language Processing (NLP) develops techniques for the analysis and interpretation of natural language, a key component of smart search engines, personal digital assistants, and many other innovative applications. The goal of this course is to provide students with a theoretical understanding of and practical experience with the advanced algorithms that power modern NLP. The course focuses on methods that involve machine learning on text data.
Recommended for
Doctoral students in computer science. Also suitable for doctoral students in cognitive science.
The course was last given
Spring 2017. The course is an adaptation of a well-established Master's-level course targeted at students in engineering (TDDE09) and cognitive science (729A27).
Goals
On completion of the course, the student should be able to:
* explain state-of-the-art NLP algorithms and analyse them theoretically
* implement NLP algorithms and apply them to practical problems
* design and carry out evaluations of NLP components and systems
* seek, assess and use scientific information within the area of NLP
Prerequisites
Discrete mathematics, data structures, and algorithms. Basic knowledge of probability theory and optimisation. Previous courses in machine learning are recommended but no requirement for the course. To do the lab assignments and the project, you should have good knowledge of programming. All of these prerequisites are negotiable; contact the examiner for details.
Contents
State-of-the-art NLP algorithms for the analysis and interpretation of words, sentences, and texts. Relevant machine learning methods based on statistical modelling, combinatorial optimisation, and neural networks. NLP applications. Validation methods. NLP tools, software libraries, and data. NLP research and development.
Organization
The course is given in the form of lectures, lab assignments, and seminars in connection with a minor project.
Literature
Lecture notes provided by the department
Lecturers
Marco Kuhlmann
Examiner
Marco Kuhlmann
Examination
Students can be examined on any subset of the following components:
* Written examination, 2 credits
* Lab assignments (basic level), 2 credits
* Lab assignments (advanced level), 2 credits
* Project assignments, 2 credits
Students who are taking this course as part of their CUGS Core obligations will
have to pick 3 components (for a total of 6 credits).
Credit
6 credits
Organized by
Department of Computer and Information Science, Linköping University
Comments
This is a CUGS Core course.
Page responsible: Director of Graduate Studies