GiellaLT provides an infrastructure for rule-based language technology aimed at minority and indigenous languages, and streamlines building anything from keyboards to speech technology. Read more about Why. See also How to get started and our Privacy document.
This site contains the technical documentation of the GiellaLT infrastructure, developed and used by Divvun and Giellatekno. It is an open source website providing analysers and tools for a wide range of languages, as well as a ready-made setup for adding more languages.
Computer tools supported by our infrastructure include:
We write our morphologies as finite state transducers in the formalisms lexc, twolc and xfst rewrite rules, and compile them into computer programs for language analysis with the compilers xfst, hfst or foma. Our syntaxes we write in constraint grammar, and we compile our constraint grammars with vislcg3. The installation of these compilers is documented on the Getting Started page.
All our resources, infrastructure and linguistic content alike, are available under dual licenses, CC-by-SA and GPL. You may thus take whatever resource you find useful with you and go, as long as you refer to us when you use it.
The linguistic source code is found in the present git repository (giellalt). In addition to that, we maintain the following git repositories (all on github), mostly with more technical content: borealium, divvun, divvungiellatekno, giellatekno. Another relevant git repository (also on github) is apertium.
You may also cooperate with us, e.g. use our servers for your language, embark on a shared project, etc. In order to do that, please contact us.