index.md

Language models (transducers)

Working with LEXC, TWOLC and Constraint Grammar

Transducers

• Transducer infrastructure
• Tutorials for lexc, twolc and constraint grammar
• Test scripts and routines for use when working on the tools
• Handling morphological variation in lexc
• Principles for common (language-independent) lexicon entries

Specialised transducers

There is machinery in place to handle systematic variation in things like orthography, writing systems, dialectal variation and geographical variation. The setup for each is documented here:

• Alternative orthographies
• Alternative Writing system (TBW)
• Dialectal variation (TBW)
• Geographic variation (TBW)

Shared resources

Description of how to set up shared resources.

Documentation of tags

These links document the different types of tags used in the grammar models.

• How the different tags are interacting with the FSTs
• Harmonising the most frekvent derivations in Saami languages
• Compoundtags
• Morphological tags
• Derivational tags
• Syntax
• Dependency
• Semantic tags

Language-specific documentation

• Work on each languages is documented on their respective pages
• Page for improving our linguistic analysis for the Saami languages

Obsolete documentation

Here we keep some documentation that now is obsolete, but that we don't want to throw away. Sometimes looking at how things were before help us understand the present situation, or it may support our memory.

• The original sme flowchart over the old infra
• The makefile setup in our old infra
• Our oldinfra system for flag diacritics"