An Updated Version of INF5820

Fall 2018 is the last time this course is offered in the study programme Informatics: Language and Communication.  Our primary target audience this term, thus, are students on this programme.  Students on other study programmes are, of course, welcome too, but incoming MSc students on the new Informatics: Language Technologies programme are discouraged from taking INF5820.  Instead, a revised variant of the class will be taught in the first half of 2019, using the new course code INF5480.

The course will be organized differently from past versions, with a heavy focus on neural (or ‘deep learning’) methods in Natural Language Processing (NLP) and on scientific computing tools and techniques that scales to potentially large data sets.  This class will teach you the basics of what you will likely be asked about in future job interviews.

We will be leaning heavily on the recent text book by Goldberg (2017).  All participants will gain access to the Abel supercluster; four obligatory assignments will combine software and model development with experimentation on standard NLP problems and data sets.  To keep everyone motivated, these assignments will jointly constitute a class-internal ‘system bake-off’ (or shared task), where the best-performing submissions will be awarded a prize of honor towards the end of the term.

If you are considering taking this class, welcome to the first overview lecture on Tuesday, August 21, 2018!  In general, we will do our utmost to encourage regular participation in lectures and laboratories, i.e. strive to create a highly interactive and enjoyable experience.