Week 1

Lecture 1: Introduction & Looking at data

Part 1: Introduction to NLP

Zoom

Presentation

Recordings:

• Part 1
• Part 2

Recommended reading

• Jurafsky and Martin, Speech and Language Processing, 2. ed., Ch. 1
• Wikipedia, "Natural Language Processing"
• Wikipedia, "Computational Linguistics"

Part 2 Looking at data

Presentation

Screen cast videos:

1. Data
2. Frequencies
3. Numeric data
4. Dispersion

Recommended reading

• Wikipedia, "Frequency (statistics)
• NLTK Book,
  • Ch.1, Sec. 3 "Computing with Language: Simple Statistics"
  • Ch.2, Sec. 2 "Conditional Frequency Distributions"

For the descriptive statistics part, any of the following will cover the lecture

• OpenIntro (3. ed.)1.1, 1.2.0- 1.2.2, 1.6.0-1.6.5, 1.7.0-1.7.2
• Moore and McCabe: Ch. 1, "Looking at Data - Distributions", sec. 1.1-1.2

Tutorial on probabilities, Tuesday 18.8 10.15 in Fortress

Sign up here!

Presentation

Background data for the corona example from FHI (in Norwegian),

Screencast videos

• Part 1
• Part 2

There were some problems with Zoom being too slow processing the material. Hence the second hour had to be recorded in PowerPoint. You may open the presentation and start the show to hear the sound.

Readings

OpenIntro (3. ed.) (In the 4th ed. add one to the chapter numbers)

• Ch. 2, "Probability", sec. 2.1-2.4
• Ch. 3, "Distributions of random variables":
  • Sec. 3.3.1 Bernoulli distribution
  • Sec. 3.4.1 Binomial distribution

Regular group sessions start Tuesday 25.8!