From Apertium
Jump to navigation Jump to search

The Balkan languages are those languages spoken in the Balkans, and possibly forming a part of the Balkan Sprachbund. They include Bulgarian, Macedonian, Romanian, Aromanian, Albanian, Greek, Serbo-Croatian, and a number of others.

The master plan involves generating independent finite-state transducers for each language, and then making individual dictionaries and transfer rules for every pair. The current status of these goals is listed below.


The ultimate goal is to have multi-purposable transducers for a variety of Balkan languages. These can then be paired for X→Y translation with the addition of a CG for language X and transfer rules / dictionary for the pair X→Y. Below is listed development progress for each language's transducers and dictionary pairs.


Once a transducer has ~80% coverage on a range of medium-large corpora we can say it is "working". Over 90% and it can be considered to be "production".

name Language ISO 639 formalism state stems coverage location primary authors
-2 -3
apertium-bul Bulgarian bg bul ? production 8,578 ~80% apertium-bul (languages) Fran, Tihomir
apertium-mkd Macedonian mk mkd ? production 30,686 ~90.5% apertium-mkd (languages) Fran, Tihomir, Petkovski
apertium-ron Romanian ro ron ? ? ? ? apertium-ron-rup (incubator) ?
apertium-rup Aromanian - rup ? ? 312,005 - apertium-rup (incubator) ?
apertium-sqi Albanian sq sqi ? development 3,312 ~80.2% apertium-sqi (languages) ?
apertium-ell Greek el ell ? ? 2,460 - apertium-ell (languages) ?
apertium-hbs Serbo-Croatian sh hbs ? working 58,004 ~90.5% apertium-hbs (languages) ?
apertium-slv Slovenian sl slv ? production 20,596 ~90.5% apertium-hbs-slv (trunk)
apertium-slv-pol (incubator)
apertium-sl-mk (incubator)
Fran, Petkovski, Peradin, Aleš Horvat, Dejan Čabrilo, Ivica Dimitrijev
apertium-tur Turkish tr tur ? working 17,221 ~87.3% apertium-tur (languages) Fran, Grossi, Sezgi Aydın

Balkan Language Classification


Existing language pairs

Balkan-Balkan pairs

Text in italic denotes language pairs under development / in the incubator. Regular text denotes a functioning language pair in staging, while text in bold denotes a stable well-working language pair in trunk.

bul mkd ron rup sqi ell hbs slv tur
bul - mk-bg bg-el
mkd - mk-sq
ron - ron-rup
rup -
sqi -
ell -
hbs sh-mk - hbs-slv
slv sl-mk -
tur -

Pairs with non-Balkan languages

bul mkd ron rup sqi ell hbs slv tur
el bg-el
ru bg-ru hbs-rus
en bg-en mk-en sh-en tr-en
it ro-it sl-it
spa slv-spa
pol slv-pol



Language Module Paradigms Lemmata Coverage (SETimes) Coverage (Wikipedia)
Bulgarian Macedonian and Bulgarian 305 7873 88.1% 77.15%
Macedonian Macedonian and Bulgarian 225 8094 92.1%
Romanian Spanish and Romanian 997 18719 89.7% 83.62%
Aromanian Incubator 17 28 -
Albanian Incubator 127 3302 80.2% 65.62%
Greek Incubator 377 859 49.4% 49.75%
Serbo-Croatian Incubator 85 660 -
Slovenian Incubator 1128 20385 -
Turkish (external: TRMorph) - 37101

Languages missing: Roma


Language pairs

See also

External links