About me

• David Lukeš
  • david.lukes@ff.cuni.cz
  • https://dlukes.github.io
  • these slides at: https://trnka.korpus.cz/~lukes/slides/v4py/intro
• Institute of the Czech National Corpus, Faculty of Arts, Charles University, Prague
• academic interests: phonetics, corpus linguistics; language evolution and acquisition
• started programming at uni, so it’s never too late :)
• probably the most useful skill since learning to read

Python gives you wings!

About you

• Who has programmed before? In what language(s)? Python?
• What’s your academic field? Linguistics, history, digital humanities…?
• Who is reasonably familiar with working with language data on a computer (e.g. corpora etc.)?
• Who knows what regular expressions are? Who uses them?
• What are you hoping to learn this week?

Python: https://www.python.org/

• a simple, fun and approachable programming language
• FLOSS (Free, Libre, Open-Source Software) × e.g. Microsoft Word
• created in 1991 by Guido van Rossum
• why is it named Python?

NLTK Book: http://www.nltk.org/book/

The NLP pipeline

What we’ll cover

• Python basics (functions, control flow, collections)
• The NLTK package & book as a good starting point for people interested in language data
• How text is represented inside computers
• Regular expressions in Python
• Accessing web services (“REST APIs”) from Python & Automatic annotation of language data (tagging, parsing) – both courtesy of Rudolf Rosa
• Getting data into Python (raw text & tabular data)
• Some visualizations (dispersion plots, wordclouds)
• Case studies: collocation strength, keyword analysis
• Hackathon on Friday!