Difference between revisions of "Balkan languages"

From Apertium
Jump to navigation Jump to search
Line 43: Line 43:
|| <code>hbs</code>
|| <code>hbs</code>
|| [[lttoolbox]]
|| [[lttoolbox]]
|| working
|| production
|align="right"| {{#lst:Apertium-hbs/stats|stems}}
|align="right"| {{#lst:Apertium-hbs/stats|stems}}
|align="right"| {{#lst:Apertium-hbs/stats|paradigms}}
|align="right"| {{#lst:Apertium-hbs/stats|paradigms}}
Line 61: Line 61:
|| [[apertium-hbs-slv]] ([[trunk]])<br />[[apertium-slv-pol]] ([[incubator]])<br />[[apertium-sl-mk]] ([[incubator]])
|| [[apertium-hbs-slv]] ([[trunk]])<br />[[apertium-slv-pol]] ([[incubator]])<br />[[apertium-sl-mk]] ([[incubator]])
|| [[User:Francis Tyers|Fran]], [[User:Fpetkovski|Petkovski]], [[User:Krvoje|Peradin]], Horvat, Čabrilo, Dimitrijev
|| [[User:Francis Tyers|Fran]], [[User:Fpetkovski|Petkovski]], [[User:Krvoje|Peradin]], Horvat, Čabrilo, Dimitrijev
|-
|| <code>[[apertium-tur]]</code>
|| [[Turkish]]
|| <code>tr</code>
|| <code>tur</code>
|| [[HFST]]
|| working
|align="right"| {{#lst:Apertium-tur/stats|stems}}
|align="right"| {{#lst:Apertium-tur/stats|paradigms}}
|align="center"| [[Apertium-tur#Current_State|~{{:Apertium-tur/stats/average}}%]]
|| [[apertium-tur]] ([[languages]])
|| [[User:Francis Tyers|Fran]], [[User:Zfe|Gianluca]], Sezgi Aydın
|-
|-
|| <code>[[apertium-bul]]</code>
|| <code>[[apertium-bul]]</code>
Line 85: Line 73:
|| [[apertium-bul]] ([[languages]])
|| [[apertium-bul]] ([[languages]])
|| [[User:Francis Tyers|Fran]], [[User:Tihomir|Tihomir]]
|| [[User:Francis Tyers|Fran]], [[User:Tihomir|Tihomir]]
|-
|| <code>[[apertium-tur]]</code>
|| [[Turkish]]
|| <code>tr</code>
|| <code>tur</code>
|| [[HFST]]
|| working
|align="right"| {{#lst:Apertium-tur/stats|stems}}
|align="right"| {{#lst:Apertium-tur/stats|paradigms}}
|align="center"| [[Apertium-tur#Current_State|~{{:Apertium-tur/stats/average}}%]]
|| [[apertium-tur]] ([[languages]])
|| [[User:Francis Tyers|Fran]], [[User:Zfe|Gianluca]], Sezgi Aydın
|-
|-
|| <code>[[apertium-sqi]]</code>
|| <code>[[apertium-sqi]]</code>
Line 103: Line 103:
|| <code>ell</code>
|| <code>ell</code>
|| [[lttoolbox]]
|| [[lttoolbox]]
|| ?
|| development
|align="right"| {{#lst:Apertium-ell/stats|stems}}
|align="right"| {{#lst:Apertium-ell/stats|stems}}
|align="right"| {{#lst:Apertium-ell/stats|paradigms}}
|align="right"| {{#lst:Apertium-ell/stats|paradigms}}
Line 115: Line 115:
|| <code>rup</code>
|| <code>rup</code>
|| [[lttoolbox]]
|| [[lttoolbox]]
|| ?
|| development
|align="right"| {{#lst:Apertium-rup/stats|stems}}
|align="right"| {{#lst:Apertium-rup/stats|stems}}
|align="right"| {{#lst:Apertium-rup/stats|paradigms}}
|align="right"| {{#lst:Apertium-rup/stats|paradigms}}
Line 127: Line 127:
|| <code>ron</code>
|| <code>ron</code>
|| [[lttoolbox]]
|| [[lttoolbox]]
|| ?
|| development
|align="right"| ?
|align="right"| ?
|align="right"| ?
|align="right"| ?

Revision as of 21:56, 24 December 2013

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.

Status

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.

Transducers

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 paradigms coverage location primary authors
-2 -3
apertium-mkd Macedonian mk mkd lttoolbox production 30,686 260 ~90.5% apertium-mkd (languages) Fran, Tihomir, Petkovski
apertium-hbs Serbo-Croatian sh hbs lttoolbox production 58,004 1,092 ~90.5% apertium-hbs (languages) Fran
apertium-slv Slovenian sl slv lttoolbox production 20,596 1,435 ~90.5% apertium-hbs-slv (trunk)
apertium-slv-pol (incubator)
apertium-sl-mk (incubator)
Fran, Petkovski, Peradin, Horvat, Čabrilo, Dimitrijev
apertium-bul Bulgarian bg bul lttoolbox production 8,578 317 ~80% apertium-bul (languages) Fran, Tihomir
apertium-tur Turkish tr tur HFST working 17,221 1 ~87.3% apertium-tur (languages) Fran, Gianluca, Sezgi Aydın
apertium-sqi Albanian sq sqi lttoolbox development 3,312 138 ~80.2% apertium-sqi (languages) Fran
apertium-ell Greek el ell lttoolbox development 2,460 951 - apertium-ell (languages) Fran
apertium-rup Aromanian - rup lttoolbox development 312,005 26193 - apertium-rup (incubator) Fran, shopskasalata
apertium-ron Romanian ro ron lttoolbox development ? ? - apertium-ron-rup (incubator) Fran

Balkan Language Classification [1]

The languages that share these similarities belong to five distinct branches of the Indo-European languages:

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-bg - mk-sq sh-mk sl-mk
ron - ron-rup
rup ron-rup -
sqi mk-sq -
ell bg-el -
hbs sh-mk - hbs-slv
slv sl-mk hbs-slv -
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 en-sq ell-eng sh-en tr-en
it ro-it sl-it
spa slv-spa
pol slv-pol
eo eo-bg eo-el
fr fr-ro
ca ca-ro
es es-ro
cs cs-sl
kir tur-kir
tat tur-tat
uzb tur-uzb
aze tur-aze
cv cv-tr

Table of dix progress

bul mkd ron rup sqi ell hbs slv tur el ru en it spa pol eo fr ca es cs kir tat uzb aze cz
bul -
mkd -
ron -
rup -
sqi -
ell -
hbs -
slv -
tur -
el -
ru -
en -
it -
spa -
pol -
eo -
fr -
ca -
es -
cs -
kir -
tat -
uzb -
aze -
cv -

Existing

Monolingual

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

Bilingual

Language pairs

See also

External links