Week 1

Lecture 1, 25 Aug.: Introduction & Looking at data

Part 1: Introduction to NLP

Presentation

Recording

(Apologies for the bad sound. We will try to do better next time.)

Recommended readings

• 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:

(Because of the bad sound in the recording from this year, we publish instead the prerecorded videos from 2020, including the Dispersion part we did not reach in the lecture.)

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

Recommended readings

• 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

Group session, Tuesday 30.8 12.15 in Sed

• Program
• Solutions