ľ�ϸ���Ӱ��

Paris is to France what London is to … Can a computer finish this sentence? Do computers understand concepts, and historical change in concepts?

We can use Natural Language Processing tools to analyze large volumes of text and find out this type of associations. When we describe concepts in texts, we use certain words which we associate with that concept. For example, when talking about a “flower” particular instances of flowers may be present in the same text, such as roses, and tulips.

In this demo by , we will show how word2vec can make this type of associations and how it can help historians explore historical development of concepts. Can such technology be useful for your research? Come along and find out how it may.

Data Science Day is this year’s edition of the annual IT Day, an initiative of Information and Technology Services (ITS) which has taken place since 2016. Each year, the event focuses on current IT trends and developments impacting education, research and work at Utrecht ľ�ϸ���Ӱ��. Depending on the theme chosen, the event is either intended for all UU colleagues (and external partners) or for a group of colleagues with a common interest.