Language Technology at UiT

The Divvun and Giellatekno teams build language technology aimed at minority and indigenous languages

View GiellaLT on GitHub divvungiellatekno/giellalt.uit.no

Čoahkkin 11.2.2013

Čoahkkimis: Trond, Lene, Ritva, Biret, Linda

Áššit

Statistihkka

Dokumentašuvdna

Seahtat

Mis leat leamaš seahtat fiilla álggus. Lea goitge vejolaš bidjat daid dasa, mis dat leat anus.

Bajilčállagat

##= !!!Verbmapping  vástida boares vuogi: #########

##= !!Verbdisambiguation  vástida boares vuogi: ------

##= !Indicative  vástida boares vuogi: - - - -

sme$ ls script/testCGrules.sh

/src/sme-dis.rle  => /src/Nsme-dis.rle

sh script/testCGrules.sh
##=!!!
##=*
##=!!
##=*
##=!
##=*
##=**
##=***
##=#
##=##
##=###

valeansa:

*LIST PA-0-V *LIST PA-ILL-V *LIST PA-ACC-IN-COM-V - PA: patient, IN:instrument *LIST IN-ACC-ANY-V

valeansatagga:
<IN-Com-Veh> vuodjit biillain

Trond: Mun sáhtán ráhkadit ođđa infra sme:ii (dušše dokumentašuvdnii)

Vislcg3 ođđa vejolašvuođat

Boares struktuvra

Bajilčállagat

  1. Delimiters
  2. Tags and sets
  3. Disambiguation rules
    1. One-cohort disambiguation - cycle 0
    2. Local disambiguation - cycles 1 and 2
    3. Cycle 1a: Special cases
    4. Cycle 1b: Cleaning up after the special cases
    5. Cycle 2: Other local disambiguation
    6. Mapping of COMP-CS<, CC and CS
    7. More diambiguation
    8. Verb mappings
    9. Disambiguating nouns
    10. Mainly mapping-rules
    11. Disambiguating nouns
      1. Case disambiguation
    12. Cycle 3: Global disambiguation
    13. Cycle 4: Syntactic disambiguation
    14. Cycle 5: Post-syntactic morphological disambiguation

Delimiters

Tags and sets

Go lea deklarerejuvvon LIST N = N ;, de ii darbbaš čállit (N) njuolggadusas.

Semánttalaš taggat: Hum lea čađahuvvon. Body ii leat (dušše okta miellahtu). Lene evttohus: Deklareret dušše daid mat leat čađahuvvon.

Bargojuohku

Boahtte čoahkkin