Norwegian Nynorsk (Apertium) documentation

This page documents the work on the Norwegian Nynorsk language model from Apertium.

It is used in some MT projects at UiT. Beyond that, the idea is to take the Apertium source files, and reuse them in the GiellaLT infrastructure (both Apertium and GiellaLT are FST based), to build spellers, analysers, and other tools.

Project documentation

• all documentation regarding the basic fst is to be found in the Apertium NNO repositorium.

In the future there might be documentation on the GiellaLT specific enhancements and changes made to the Apertium analyser.

In-source documentation

Below is an autogenerated list of documentation pages built from structured comments in the source code. All pages are also concatenated and can be read as one long text here.

• src/
  • cg3/
    • disambiguator.cg3 (src)
    • functions.cg3 (src)
  • fst/
    • affixes/
      • symbols.lexc (src)
    • root.lexc (src)
  • phonetics/
    • txt2ipa.xfscript (src)
  • transcriptions/
    • transcriptor-abbrevs2text.lexc (src)
    • transcriptor-numbers-digit2text.lexc (src)
• tools/
  • grammarcheckers/
    • grammarchecker.cg3 (src)
  • tokenisers/
    • tokeniser-disamb-gt-desc.pmscript (src)
    • tokeniser-gramcheck-gt-desc.pmscript (src)