Three Natural-Language Processing Course Modules in Oslo

Original article was published by Alex Moltzau 莫战 on Artificial Intelligence on Medium


Three Natural-Language Processing Course Modules in Oslo

If you live in Oslo these and have an interest in language technology these course modules may be of interest

Oslo is my hometown, so I decided to have a quick look at what kind of modules that are being offered within natural-language processing in Oslo the year 2020. Within this there might be more, however I found three course models mainly based within the institute of informatics at the University of Oslo:

  • IN2110 — Methods in Language Technology.
  • IN4080 — Natural Language Processing.
  • IN5550 — Neural Methods in Natural Language Processing & IN9550 — Neural Methods in Natural Language Processing.

What I can say straight away is that there is a lot of useful information out there. It must be mentioned straight away that the last two courses are largely similar and have overlapping credits, so I listed them as three courses. There is also a bachelor’s programme in language technology (språkteknologi), and they have an introduction course. Still, since this is not in English I thought it would be slightly challenging to include in this short overview.

It must be mentioned that some of these courses post some wonderful resources that are freely available online, truly amazing. This includes presentation slides. Here is an example from IN5550:

Really kind of them to share it online.

I will make a short list attempting to shortly summarise some course descriptions underneath. This is based on the text on each course module site, however it is interesting to see and understand what is currently being taught within these courses.

I thought it would be great to line up the learning outcomes to see what these courses intend to teach. I have abbreviated the description of the course content, however I have linked each course at the bottom of each description. Description for IN2110 — Methods in Language Technology is in Norwegian and you will therefore not find it here.

IN4080 — Natural Language Processing

Course content

Mean to be an overview course for NLP, emphasis on probabilistic and machine learning (ML) techniques. Mainly based on ML applied to language data. Additionally it shows steps in a typical NLP system like tagging, parsing, named entity recognition, relation extraction will be considered. This course is meant to prepare the students for a master’s thesis in Informatics: Language Technology.

Learning outcome

“After completing IN4080:

  • You are familiar with the most central applications of Natural Language Processing (NLP) and have in-depth knowledge of at least one application
  • You are familiar with the central research methods and technologies used in NLP
  • You can carry out NLP experiments involving machine learning and evaluate the results
  • You are familiar with the steps in a typical NLP system and you are able to select and apply tools for these steps
  • You are familiar with the concept of probability and how it is applied in NLP methods and in evaluation”

IN5550 — Neural Methods in Natural Language Processing

Course content

Advanced techniques in NLP with recent and current research literature. Machine learning and specifically ‘deep’ neural network approaches to the automated analysis of natural language text. Classification using Convolutional Neural Networks, and applications of various types of Recurrent Neural Networks to sequence labeling and the analysis of grammatical or semantic structure.

Learning outcome

“Upon completion of this course you:

  • are familiar with common techniques for learning dense representations (‘embeddings’) of natural language;
  • understand the basics of various types of neural networks and their applications to natural language processing;
  • can apply off-the-shelf NLP tools in meaningful ways to the data preparation for representation learning;
  • have basic knowledge of the concepts of transfer and multi-task learning in application to natural language problems;
  • can design, excecute, analyze, and summarize large-scale experiments in common neural network toolkits;
  • know how to assess the benefits and challenges of neural learning in contrast to other common approaches in NLP;
  • are able to identify and critically read relevant NLP research literature.”

10 credits overlap with IN9550 — Neural Methods in Natural Language Processing.

Activities and lectures

Within these courses you can find a list of activities for the specific lectures with links to ‘screen’ and ‘print’.

In addition to this there is a link to relevant articles as well as a few YouTube lectures:

As can be seen from this there is a variety of information that could be interesting for those who are interested in learning more about natural-language processing.