Linguistic modelling

Our research and development is based on modelling of the grammar of each individual language. Here you find documentation of the modelling of the grammars of each individual language. The modelling technique we use is Finite state transducers for morphology and Constraint Grammar for syntax. In our source code, the actual files for each of the languages are found in subcatalogues under the catalogue langs/ with similar structures, described here. Languages with no work done so far are marked with an asterisk, and found in the catalogue startup-langs/. Our research publications on these programs are found on our publication page, and information on practical programs are found behind the tabs above.

Publications and presentations

Publications on linguistic modelling

Saami languages

North, Lule, South, Inari, Kildin, Pite, Skolt

Other Finnic languages

Estonian 1, Estonian 2, Finnish, Ingrian, Kven, Livonian, Olonetsian, Veps, Võro,

Other Uralic languages

Eastern Mari, Erzya, Khanty, Komi Zyryan, Moksha, Nganasan, Northern Mansi, Tundra Nenets, Udmurt, Western Mari, Selkup

North American languages

Greenlandic, Iñupiaq, Northern Haida, Ojibwe (Chippewa), Plains Cree, Cherokee, Dogrib, Kiowa, Ojibwa, Southern Puget Sound Salish (Lushootseed), Tsuut’ina (Sarcee), Upper Necaxa Totonac, Upper Tanana

Other languages

Bashkir, Buriat, Cornish, Evenki*, Faroese, Irish*, Khalkha Mongolian*, Khakas*, Latvian, Norwegian Bokmål, Romanian, Aromanian, Russian, Somali, Klingon*, Tuvan*, Kalmyk*, Todo Oirat*,

*) = Languages with no real work done, found in startup-langs/.