docu-statusquo.eng

This document gives a short status report of the Komi grammatical analyser  and its source files.

Status for the source files:

• Lexicon: The lexicon contains 35806 entries (19129 nouns, 12191 verbs, 4486 adjectives)
• Morphology: The morphology files are 3494 lines long, and contain 479 continuation lexica. Compared to 8234 lines and 1309 lexica for Erzya, there is still work to do.
• Morphophonology: The file kpv-phon.twolc is 253 lines long. Compared to the one for Erzya, 514 lines, the situation is not that bad for Komi.

Tasks ahead:

1. Test and correct the morphology and morphophonology
2. Integrate the Komi-Russian dictionary in the analyser (done)
3. Add more words:
   1. Test the resulting analyser against text material, and add new words
   2. Systematically add Russian loanwords: names and technical terms (partly done)
4. Work on the spellchecker
   1. TODO: Collect error corpus