Omorfi Open morphology for Finnish

• Home
• Meta
• Articles
• Timeline
• TODO
• Releases
• News
• Contributing or helping
• AUTHORS
• Design
• Omorfi with moses
• Finnish morphosyntax
• Directory layout
• Database processing
• Statistics
• Speed tests
• Paradigms and stuffs
• Lexical statistics
• Inflection tables nominals
• Inflection paradigms by example
• Inflection paper dictionaries
• Faithfulness tests
• CoveragesTop100Deltas
• Coverages
• Automata sizes
• API Documentation
• Python API
• Java API
• Man pages
• omorfi-spell(1)
• omorfi-segment(1)
• omorfi-generate(1)
• omorfi-disambiguate-factorise(1)
• omorfi-disambiguate-text(1)
• omorfi-analyse-tokenised(1)
• omorfi-analyse-text(1)
• omorfi-analyse(1)

Omorfi as part of moses

Omorfi can be easily plugged into statistical machine translation system moses with semi-good results (no immediate BLEU increase or such, slight up in human evaluations).

Factored stuff

You can use omorfi as a factored model. The helper script located in src/python/omorfi-factorise.py can produce output with four factors pulled from 1-best list of omorfi installation. The factors are:

• (surface)
• lemma
• Google universal pos
• full morphological analysis
• suffix morphs

Apart from suffix morph factor, the things are standard. If you follow factored tutorial

Segmenting as pre- or post-processing

You can use omorfi to turn moses baseline phrase-based model into a morph-phrase machine translation by simply pre-processing the Finnish data with the helper script src/python/omorfi-segment.sh.