Tartu Apertium Course

Tartu Apertium Course

Tartu, Estonia

2nd October — 13th October

Programme

Main: Detailed programme

Week 1
Day	Time	Material
Monday (2nd October)	10:00 — 12:00	Introduction
	14:00 — 18:00	Installation and setup
Tuesday (3rd October)	10:00 — 12:00	Morphological dictionaries
	16:00 — 18:00	Morphological dictionaries
Thursday (5th October)	10:00 — 12:00	Morphological disambiguation
	14:00 — 18:00	Morphological disambiguation
Friday (6th October)	10:00 — 12:00	Lexical transfer
	14:00 — 18:00	Lexical transfer
Week 2
Day	Time	Material
Monday (9th October)	10:00 — 12:00	Lexical selection
	14:00 — 18:00	Lexical selection
Tuesday (10th October)	10:00 — 12:00	Structural transfer
	16:00 — 18:00	Structural transfer
Thursday (11th October)	10:00 — 12:00	Structural transfer
	14:00 — 18:00	Data consistency and quality
Friday (12th October)	10:00 — 12:00	Data consistency and quality
	14:00 — 18:00	Project planning, question and answer

Papers

You can use this as a template for your course report:

• A free/open-source Kazakh-Tatar machine translation system

Sessions

• Session 0
• Session 1
• Session 2
• Session 3
• Session 4
• Session 5
• Session 6
• Session 7

Hacks

Multichar symbols

are yours defined ?

cat apertium-est.est.lexc | grep -o '%<[^>]\+>' | sort -u | tr -d '%' > /tmp/lexc-tags
hfst-summarise -S est.automorf.hfst | grep -o '<[^>]\+>' | sort -u > /tmp/hfst-tags
comm /tmp/hfst-tags /tmp/lexc-tags

External links

• Tartu Ülikool: Rule-based machine translation
• Grammar sketch of North Sámi
• Slides
• Fran's code (look at tags and word forms)