pitkant/atp_kurssi

ATP_kurssi

This page includes all the materials for the course KKLT0030 Automatic text processing 5 credits.

The course Moodle page has private materials, such as possible recordings and announcements: https://moodle.utu.fi/course/view.php?id=29596

Mon Oct 23

• Getting started
• Notebook 1
• Commands
  • Getting data and printing stuff: wget, echo
  • Printing files: cat, head, tail
  • Copying, renaming, removing: cp, rm, mv
  • Others: wc -w, ls

Thur Oct 26

• Notebook2
• Commands: egrep, sort, uniq
• Options
  • egrep -v, -i, -w, -c, -B, -A
  • head -n, tail -n
  • wc -l, -w
  • uniq -c, sort -r, -n
• Pipes, especially frequency counts
  • sort | uniq -c | sort -rn

Mon Oct 30

• Notebook3 exercises

Thur Nov 2

• Notebook4
• Git clone for cloning Github reports
• Gzipped files using gzip and zcat
• Changing characters using tr
  • Combining tr to a frequency list pipeline
  • Using tr to normalize
• Regular expressions

Mon Nov 6

• Notebook 5 exercies

Thur Nov 9

• Notebook 6
• Dependency syntax analysis pipeline
• Sentence + token segmentation, lemmatisation, POS, dependencies
• conllu format
• Universal dependencies treebanks
• Trankit parser

Mon Nov 13

• Notebook 7
• Running python scripts

Thur Nov 16

• Notebook 8
• Working on the server (Note that the exam will be on server!)

Mon Nov 20

• Notebook 8 cont'd
• Scripts

Thur Nov 23

• Notebook 9

Mon Nov 27

• Notebook 9

Thur Nov 30

• Notebook 10
• For loops

Mon Dec 4

• Recap
• Notebook 11
• In case the Notebook 11 is not accessible as from the Github repo, you can use this version: https://colab.research.google.com/drive/16EFdusy496svEkMSxTvP0pHtzTZikHer?usp=sharing

Thur Dec 7

• Exam, option 1
• 14.00-16.00 (TBA)

Thur Dec 14

• Exam, option 2
• 14.00-16.00 (TBA)