Natural Language Processing in 10 Lines of Code

Andraz Hribernik | Thursday 14:00 | Room 2.32

Do you know that there are over 150 personal names mentioned in Jane Austen's Pride & Prejudice? Did you ever want to remove common words such as 'we', 'what', and 'for' from text? Or how to extract interesting keywords from a document? Did you know all of this could be done in 10 lines of Python code?

In this workshop we will answer these and similar questions using the open source library spaCy. One hour spent with us will be useful for anybody who is interested in text processing, text information extraction or text related data science. You will leave with the tools and knowledge to start developing your own natural language processing projects in Python. No prior experience with NLP or data science is required for this workshop, however some Python experience is needed to get the most out of the event. We would like to encourage you to install spaCy in advance, installation instructions can be found at our workshop repo on GitHub.