Natural language processing

Course goals

After completing this course the student is able to:

• build models of linguistic structure for language processing
• understand and implement supervised (and unsupervised) estimation methods for these models
• understand and implement search strategies and algorithms to process these structures (e.g. syntactic parsing)
• use these techniques in NLP applications

Assessment
The course is graded as follows:

• exam (50% of the final mark)
• assignments (50%)

To qualify for a repair of the final result the mark needs to be at least a 4, or “AANV”.

Content

This course is an advanced introduction to the study of language from a computational perspective, and to the fields of computational linguistics (CL)/Natural Language processing (NLP).  
It synthesizes research from linguistics and computer science and covers formal models for representing and analyzing words, sentences and documents.
Students will learn how to analyze sentences algorithmically, and how to build interpretable semantic representations, emphasizing data-driven and machine learning approaches and algorithms.  
The course will cover a number of standard models and algorithms  (language models, HMMs, chart and transition based syntactic parsing distributed semantic models, various neural network models) that are used throughout NLP and applications of these methods in tasks such as machine translation or text summarization.

Course form
Lectures, tutorials.

Literature
To be announced.