Creation of Morphological Parsers for Minority Finno-Ugrian Languages

Project Details

Description

Open-source morphological parsers for minority Uralic languages outside of Finland. The project utilizes Giellatekno infrastructure to produce hfst-transducers with reusable word list components. 20,000 lemmas with Finnish glosses for each target language in the time frame 2013-2014. The target languages, pending approval, include: Livvi Karelian, Hill Mari, Veps, Nenets, Moksha and LIvonian. Other languages included in the project to a lesser extent are Erzya, Meadow Mari, Ingrian, Komi, Võro, Udmurt and Nganasan.
StatusFinished
Effective start/end date01/01/201331/12/2014

Fields of Science

  • 6121 Languages
  • Moksha language
  • Olonets language
  • Hill Mari language
  • Livonian language
  • Nenets language
  • HFST
  • open source code
  • Finno-Ugrian languages
  • Uralic languages
  • morphology
  • Spell checkers
  • vähemmistökielet
  • uralilaiset kielet
  • Finnish Glossing
  • Finnish as a scientific language
  • Kone Language Programme
  • Ingrian language
  • Erzya language
  • Meadow Mari language
  • finite-state transducer
  • Giellatekno
  • Nganasan language
  • Shoksha language
  • Võro language
  • Morphology-savvy