I’m giving a workshop at the University of Calgary’s Language Research Centre on the 16th of November 2018 (Craigie Hall D420, 9-10:30 am). Here’s the abstract:
A Gentle Introduction to Natural Language Processing
Natural Language Processing (NLP) is less intimidating than its name suggests. It’s just using a computer to process texts written in ‘natural’ (i.e. non-computer) languages like English, Estonian, or Esperanto. It slices those texts into lists of words, and then it does things with those words: counting, sorting, categorizing, comparing, transforming, substituting, and visualizing them. (Here’s my introduction and tutorial on some of these basic functions.) NLP is behind every phrase you Google, and every query you pose to Siri or Alexa; but what concerns us in this workshop is its potential for language research. You’ll learn how to collect and process texts, and how to run algorithms that quantify your qualitative inquiries. A case study will be my work detecting rhetorical figures like chiasmus in Shakespeare (“Fair is foul, and foul is fair”). To benefit from this workshop you need no programming experience, only a willingness to treat texts as data.