Difference between revisions of "Balkan languages"

From Apertium
Jump to navigation Jump to search
 
(46 intermediate revisions by 5 users not shown)
Line 1: Line 1:
 
{{TOCD}}
 
{{TOCD}}
'''Balkan languages''' are those languages spoken in the Balkans, and possibly forming a part of the Balkan Sprachbund.
+
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.
==Existing==
 
   
===Monolingual===
+
==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===
{|class="wikitable"
 
  +
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".
! Language !! Module !! Paradigms !! Lemmata !! Coverage (SETimes) !! Coverage (Wikipedia)
 
  +
|-
 
  +
{| class="wikitable sortable"
| Bulgarian || [[Macedonian and Bulgarian]] || 305 || 5269 || 87.7% || 76.72%
 
|-
 
| Macedonian || [[Macedonian and Bulgarian]] || 225 || 5408 || 91.4% ||
 
 
|-
 
|-
  +
!rowspan=2| name
| Romanian || [[Spanish and Romanian]] || 997 || 18719 || 89.67% || 83.62%
 
  +
!rowspan=2| Language
  +
!colspan=2 class="unsortable"| ISO 639
  +
!rowspan=2| formalism
  +
!rowspan=2| state
  +
!rowspan=2| stems
  +
!rowspan=2| paradigms
  +
!rowspan=2| coverage
  +
!rowspan=2| location
  +
!rowspan=2 class="unsortable"| primary authors
  +
|-class="sortbottom"
  +
! -2
  +
! -3
 
|-
 
|-
  +
|| <code>[[apertium-mkd]]</code>
| Albanian || [[Incubator]] || 57 || 9794 || 61.92% || 57.76%
 
  +
|| [[Macedonian]]
  +
|| <code>mk</code>
  +
|| <code>mkd</code>
  +
|| [[lttoolbox]]
  +
|| production
  +
|align="right"| {{#lst:Apertium-mkd/stats|stems}}
  +
|align="right"| {{#lst:Apertium-mkd/stats|paradigms}}
  +
|align="center"| [[Apertium-mkd#Current_State|~{{:Apertium-mkd/stats/average}}%]]
  +
|| [[apertium-mkd]] ([[languages]])
  +
|| [[User:Francis Tyers|Fran]], [[User:Tihomir|Tihomir]], [[User:Fpetkovski|Petkovski]]
 
|-
 
|-
  +
|| <code>[[apertium-hbs]]</code>
| Greek || [[Incubator]] || 377 || 859 || 49.43% || 49.75%
 
  +
|| [[Serbo-Croatian]]
  +
|| <code>sh</code>
  +
|| <code>hbs</code>
  +
|| [[lttoolbox]]
  +
|| production
  +
|align="right"| {{#lst:Apertium-hbs/stats|stems}}
  +
|align="right"| {{#lst:Apertium-hbs/stats|paradigms}}
  +
|align="center"| [[Apertium-hbs#Current_State|~{{:Apertium-hbs/stats/average}}%]]
  +
|| [[apertium-hbs]] ([[languages]])
  +
|| [[User: Francis Tyers|Fran]], [[User:Fpetkovski|Petkovski]], Aleš, [[User:Krvoje|hrvoj]]
 
|-
 
|-
  +
|| <code>[[apertium-slv]]</code>
| Serbo-Croatian || [[Incubator]] || 85 || 660 || 87.62% ||
 
  +
|| [[Slovenian]]
  +
|| <code>sl</code>
  +
|| <code>slv</code>
  +
|| [[lttoolbox]]
  +
|| production
  +
|align="right"| {{#lst:Apertium-slv/stats|stems}}
  +
|align="right"| {{#lst:Apertium-slv/stats|paradigms}}
  +
|align="center"| [[Apertium-slv#Current_State|~{{:Apertium-slv/stats/average}}%]]
  +
|| [[apertium-hbs-slv]] ([[trunk]])<br />[[apertium-slv-pol]] ([[incubator]])<br />[[apertium-sl-mk]] ([[incubator]])
  +
|| [[User:Francis Tyers|Fran]], [[User:Fpetkovski|Petkovski]], [[User:Krvoje|Peradin]], Aleš, Čabrilo, Dimitrijev
 
|-
 
|-
  +
|| <code>[[apertium-bul]]</code>
| Turkish || (''external'' [http://www.let.rug.nl/~coltekin/trmorph/ TRMorph]) || - || 37101 || ||
 
  +
|| [[Bulgarian]]
  +
|| <code>bg</code>
  +
|| <code>bul</code>
  +
|| [[lttoolbox]]
  +
|| production
  +
|align="right"| {{#lst:Apertium-bul/stats|stems}}
  +
|align="right"| {{#lst:Apertium-bul/stats|paradigms}}
  +
|align="center"| [[Apertium-bul#Current_State|~{{:Apertium-bul/stats/average}}%]]
  +
|| [[apertium-bul]] ([[languages]])
  +
|| [[User:Francis Tyers|Fran]], [[User:Tihomir|Tihomir]]
 
|-
 
|-
  +
|| <code>[[apertium-tur]]</code>
  +
|| [[Turkish]]
  +
|| <code>tr</code>
  +
|| <code>tur</code>
  +
|| [[HFST]]
  +
|| development
  +
|align="right"| {{#lst:Apertium-tur/stats|stems}}
  +
|align="right"| -
  +
|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>
  +
|| [[Albanian]]
  +
|| <code>sq</code>
  +
|| <code>sqi</code>
  +
|| [[lttoolbox]]
  +
|| development
  +
|align="right"| {{#lst:Apertium-sqi/stats|stems}}
  +
|align="right"| {{#lst:Apertium-sqi/stats|paradigms}}
  +
|align="center"| [[Apertium-sqi#Current_State|~{{:Apertium-sqi/stats/average}}%]]
  +
|| [[apertium-sqi]] ([[languages]])
  +
|| [[User: Francis Tyers|Fran]]
  +
|-
  +
|| <code>[[apertium-ell]]</code>
  +
|| [[Greek]]
  +
|| <code>el</code>
  +
|| <code>ell</code>
  +
|| [[lttoolbox]]
  +
|| prototype
  +
|align="right"| {{#lst:Apertium-ell/stats|stems}}
  +
|align="right"| {{#lst:Apertium-ell/stats|paradigms}}
  +
|align="center"| -
  +
|| [[apertium-ell]] ([[languages]])
  +
|| [[User:Francis Tyers|Fran]]
  +
|-
  +
|| <code>[[apertium-rup]]</code>
  +
|| [[Aromanian]]
  +
|| <code>-</code>
  +
|| <code>rup</code>
  +
|| [[lttoolbox]]
  +
|| prototype
  +
|align="right"| {{#lst:Apertium-rup/stats|stems}}
  +
|align="right"| {{#lst:Apertium-rup/stats|paradigms}}
  +
|align="center"| -
  +
|| [[apertium-rup]] ([[incubator]])
  +
|| [[User: Francis Tyers|Fran]], [[User:Shopskasalata|shopskasalata]]
  +
|-
  +
|| <code>[[apertium-ron]]</code>
  +
|| [[Romanian]]
  +
|| <code>ro</code>
  +
|| <code>ron</code>
  +
|| [[lttoolbox]]
  +
|| possibly non-existant
  +
|align="right"| ?
  +
|align="right"| ?
  +
|align="center"| -
  +
|| [[apertium-ron-rup]] ([[incubator]])
  +
|| [[User: Francis Tyers|Fran]]
 
|}
 
|}
   
  +
=== Balkan Language Classification===
Languages missing: Aromanian, Roma
 
  +
The languages that share these similarities belong to five distinct branches of the Indo-European languages<sup><small>[https://en.wikipedia.org/wiki/Balkan_language_area#Languages]</small></sup>:
  +
* '''[[Albanian]]''': Arvanitika, Gheg, Tosk
  +
* '''[[Hellenic languages]]''': [[Greek|Standard Greek]], Cappadocian Greek, Pontic Greek
  +
* '''[[Romance languages]]''': [[Aromanian]], [[Romanian]], [[Moldovan]], Istro-Romanian, Megleno-Romanian
  +
* '''[[Slavic languages]]'''
  +
** '''[[Western South Slavic]]''': [[Serbo-Croatian]], [[Slovenian]]
  +
** '''[[Eastern South Slavic]]''': [[Bulgarian]], [[Macedonian]]
  +
* '''[[Indic languages]]''': [[Romani]]
   
  +
=== Existing language pairs ===
===Bilingual===
 
  +
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.
  +
  +
{| style="text-align: center;" class="wikitable dixtable"
  +
|- style="background: #ececec"
  +
! !! mkd !! hbs !! slv !! bul !! tur !! sqi !! ell !! rup !! ron
  +
|-
  +
| '''mkd''' || - || '''[[Apertium-hbs-mkd|hbs-mkd]]'''<br>'''{{#lst:Apertium-hbs-mkd/stats|hbs-mkd_stems}}''' || ''[[Apertium-sl-mk|sl-mk]]''<br>{{#lst:Apertium-sl-mk/stats|sl-mk_stems}} || '''[[Apertium-mk-bg|mk-bg]]'''<br>'''{{#lst:Apertium-mk-bg/stats|mk-bg_stems}}''' || || ''[[Apertium-mk-sq|mk-sq]]''<br>{{#lst:Apertium-mk-sq/stats|mk-sq_stems}} || || ||
  +
|-
  +
| '''hbs''' || '''[[Apertium-hbs-mkd|hbs-mkd]]'''<br>'''{{#lst:Apertium-hbs-mkd/stats|hbs-mkd_stems}}''' || - || '''[[Apertium-hbs-slv|hbs-slv]]'''<br>'''{{#lst:Apertium-hbs-slv/stats|hbs-slv_stems}}''' || || || || || ||
  +
|-
  +
| '''slv''' || ''[[Apertium-sl-mk|sl-mk]]''<br>{{#lst:Apertium-sl-mk/stats|sl-mk_stems}} || '''[[Apertium-hbs-slv|hbs-slv]]'''<br>'''{{#lst:Apertium-hbs-slv/stats|hbs-slv_stems}}''' || - || || || || || ||
  +
|-
  +
| '''bul''' || '''[[Apertium-mk-bg|mk-bg]]'''<br>'''{{#lst:Apertium-mk-bg/stats|mk-bg_stems}}''' || || || - || || || ''[[Apertium-bg-el|bg-el]]''<br>{{#lst:Apertium-bg-el/stats|bg-el_stems}} || ||
  +
|-
  +
| '''tur''' || || || || || - || || || ||
  +
|-
  +
| '''sqi''' || ''[[Apertium-mk-sq|mk-sq]]''<br>{{#lst:Apertium-mk-sq/stats|mk-sq_stems}} || || || || || - || || ||
  +
|-
  +
| '''ell''' || || || || ''[[Apertium-bg-el|bg-el]]''<br>{{#lst:Apertium-bg-el/stats|bg-el_stems}} || || || - || ||
  +
|-
  +
| '''rup''' || || || || || || || || - || ''[[Apertium-ron-rup|ron-rup]]''<br>{{#lst:Apertium-ron-rup/stats|ron-rup_stems}}
  +
|-
  +
| '''ron''' || || || || || || || || ''[[Apertium-ron-rup|ron-rup]]''<br>{{#lst:Apertium-ron-rup/stats|ron-rup_stems}} || -
  +
|-
  +
| || || || || || || || || ||
  +
|-
  +
| '''aze''' || || || || || [[Apertium-tur-aze|tur-aze]]<br>{{#lst:Apertium-tur-aze/stats|tur-aze_stems}} || || || ||
  +
|-
  +
| '''cat''' || || || || || || || || || [[Apertium-ca-ro|ca-ro]]<br>{{#lst:Apertium-ca-ro/stats|ca-ro_stems}}
  +
|-
  +
| '''ces''' || || ''[[Apertium-ces-hbs|ces-hbs]]''<br>{{#lst:Apertium-ces-hbs/stats|ces-hbs_stems}} || ''[[Apertium-cs-sl|cs-sl]]''<br>{{#lst:Apertium-cs-sl/stats|cs-sl_stems}} || || || || || ||
  +
|-
  +
| '''chv''' || || || || || ''[[Apertium-cv-tr|cv-tr]]''<br>{{#lst:Apertium-cv-tr/stats|cv-tr_stems}} || || || ||
  +
|-
  +
| '''eng''' || '''[[Apertium-mk-en|mk-en]]'''<br>'''{{#lst:Apertium-mk-en/stats|mk-en_stems}}''' || '''[[Apertium-hbs-eng|hbs-eng]]'''<br>'''{{#lst:Apertium-hbs-eng/stats|hbs-eng_stems}}''' || ''[[Apertium-sl-en|sl-en]]''<br>{{#lst:Apertium-sl-en/stats|sl-en_stems}} || [[Apertium-bg-en|bg-en]]<br>{{#lst:Apertium-bg-en/stats|bg-en_stems}} || ''[[Apertium-tr-en|tr-en]]''<br>{{#lst:Apertium-tr-en/stats|tr-en_stems}} || ''[[Apertium-en-sq|en-sq]]''<br>{{#lst:Apertium-en-sq/stats|en-sq_stems}} || ''[[Apertium-ell-eng|ell-eng]]''<br>{{#lst:Apertium-ell-eng/stats|ell-eng_stems}} || ||
  +
|-
  +
| '''epo''' || || || || ''[[Apertium-eo-bg|eo-bg]]''<br>{{#lst:Apertium-eo-bg/stats|eo-bg_stems}} || ''[[Apertium-eo-tr|eo-tr]]''<br>{{#lst:Apertium-eo-tr/stats|eo-tr_stems}} || || ''[[Apertium-eo-el|eo-el]]''<br>{{#lst:Apertium-eo-el/stats|eo-el_stems}} || ||
  +
|-
  +
| '''fin''' || || ''[[Apertium-fin-hbs|fin-hbs]]''<br>{{#lst:Apertium-fin-hbs/stats|fin-hbs_stems}} || || || || || || ||
  +
|-
  +
| '''fra''' || || || || || || || || || ''[[Apertium-fr-ro|fr-ro]]''<br>{{#lst:Apertium-fr-ro/stats|fr-ro_stems}}
  +
|-
  +
| '''ina''' || || || || || || || || || ''[[Apertium-ron-ina|ron-ina]]''<br>{{#lst:Apertium-ron-ina/stats|ron-ina_stems}}
  +
|-
  +
| '''ita''' || || || ''[[Apertium-slv-ita|slv-ita]]''<br>{{#lst:Apertium-slv-ita/stats|slv-ita_stems}} || || || || || || [[Apertium-ro-it|ro-it]]<br>{{#lst:Apertium-ro-it/stats|ro-it_stems}}
  +
|-
  +
| '''kir''' || || || || || [[Apertium-tur-kir|tur-kir]]<br>{{#lst:Apertium-tur-kir/stats|tur-kir_stems}} || || || ||
  +
|-
  +
| '''pol''' || || ''[[Apertium-pol-hbs|pol-hbs]]''<br>{{#lst:Apertium-pol-hbs/stats|pol-hbs_stems}} || ''[[Apertium-slv-pol|slv-pol]]''<br>{{#lst:Apertium-slv-pol/stats|slv-pol_stems}} || || || || || ||
  +
|-
  +
| '''rus''' || || [[Apertium-hbs-rus|hbs-rus]]<br>{{#lst:Apertium-hbs-rus/stats|hbs-rus_stems}} || || ''[[Apertium-bg-ru|bg-ru]]''<br>{{#lst:Apertium-bg-ru/stats|bg-ru_stems}} || || || || ||
  +
|-
  +
| '''spa''' || || || [[Apertium-slv-spa|slv-spa]]<br>{{#lst:Apertium-slv-spa/stats|slv-spa_stems}} || || || || || || '''[[Apertium-es-ro|es-ro]]'''<br>'''{{#lst:Apertium-es-ro/stats|es-ro_stems}}'''
  +
|-
  +
| '''tat''' || || || || || [[Apertium-tur-tat|tur-tat]]<br>{{#lst:Apertium-tur-tat/stats|tur-tat_stems}} || || || ||
  +
|-
  +
| '''tuk''' || || || || || [[Apertium-tuk-tur|tuk-tur]]<br>{{#lst:Apertium-tuk-tur/stats|tuk-tur_stems}} || || || ||
  +
|-
  +
| '''uzb''' || || || || || [[Apertium-tur-uzb|tur-uzb]]<br>{{#lst:Apertium-tur-uzb/stats|tur-uzb_stems}} || || || ||
  +
|}
  +
  +
== Samples ==
  +
Article 1 of the Universal Declaration of Human Rights:
  +
  +
''All human beings are born free and equal in dignity and rights. They are endowed with reason and conscience and should act towards one another in a spirit of brotherhood.''
  +
  +
{|class=wikitable
  +
! Language !! Text
  +
|-
  +
|| Macedonian || Сите човечки суштества се раѓаат слободни и еднакви по достоинство и права. Тие се обдарени со разум и совест и треба да се однесуваат еден кон друг во духот на општо човечката припадност.
  +
|-
  +
|| Slovenian || Vsi ljudje se rodijo svobodni in imajo enako dostojanstvo in enake pravice. Obdarjeni so z razumom in vestjo in bi morali ravnati drug z drugim kakor bratje.
  +
|-
  +
|| Bulgarian || Всички хора се раждат свободни и равни по достойнство и права. Те са надарени с разум и съвест и следва да се отнасят помежду си в дух на братство.
  +
|-
  +
|| Turkish || Bütün insanlar hür, haysiyet ve haklar bakımından eşit doğarlar. Akıl ve vicdana sahiptirler ve birbirlerine karşı kardeşlik zihniyeti ile hareket etmelidirler.
  +
|}
   
 
==See also==
 
==See also==
Line 37: Line 232:
 
* [http://www.let.rug.nl/~coltekin/trmorph/ TRMorph]
 
* [http://www.let.rug.nl/~coltekin/trmorph/ TRMorph]
   
[[Category:Balkan languages]]
+
[[Category:Languages of the Balkans]]

Latest revision as of 19:27, 27 August 2017

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[edit]

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[edit]

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, Petkovski, Aleš, hrvoj
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, Aleš, Čabrilo, Dimitrijev
apertium-bul Bulgarian bg bul lttoolbox production 8,578 317 ~80% apertium-bul (languages) Fran, Tihomir
apertium-tur Turkish tr tur HFST development 17,221 - ~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 prototype 2,460 951 - apertium-ell (languages) Fran
apertium-rup Aromanian - rup lttoolbox prototype 312,005 26193 - apertium-rup (incubator) Fran, shopskasalata
apertium-ron Romanian ro ron lttoolbox possibly non-existant ? ? - apertium-ron-rup (incubator) Fran

Balkan Language Classification[edit]

The languages that share these similarities belong to five distinct branches of the Indo-European languages[1]:

Existing language pairs[edit]

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.

mkd hbs slv bul tur sqi ell rup ron
mkd - hbs-mkd
12,813
sl-mk
25,579
mk-bg
8,783
mk-sq
?
hbs hbs-mkd
12,813
- hbs-slv
24,717
slv sl-mk
25,579
hbs-slv
24,717
-
bul mk-bg
8,783
- bg-el
638
tur -
sqi mk-sq
?
-
ell bg-el
638
-
rup - ron-rup
402
ron ron-rup
402
-
aze tur-aze
8,194
cat ca-ro
16,431
ces ces-hbs
167
cs-sl
570
chv cv-tr
100
eng mk-en
33,350
hbs-eng
16,228
sl-en
313
bg-en
10,242
tr-en
171
en-sq
580
ell-eng
830
epo eo-bg
?
eo-tr
1,500
eo-el
1,150
fin fin-hbs
250
fra fr-ro
12,727
ina ron-ina
192
ita slv-ita
1,586
ro-it
10,093
kir tur-kir
7,123
pol pol-hbs
136
slv-pol
354
rus hbs-rus
5,008
bg-ru
3,292
spa slv-spa
es-ro
24,528
tat tur-tat
3,317
tuk tuk-tur
3,387
uzb tur-uzb
3,519

Samples[edit]

Article 1 of the Universal Declaration of Human Rights:

All human beings are born free and equal in dignity and rights. They are endowed with reason and conscience and should act towards one another in a spirit of brotherhood.

Language Text
Macedonian Сите човечки суштества се раѓаат слободни и еднакви по достоинство и права. Тие се обдарени со разум и совест и треба да се однесуваат еден кон друг во духот на општо човечката припадност.
Slovenian Vsi ljudje se rodijo svobodni in imajo enako dostojanstvo in enake pravice. Obdarjeni so z razumom in vestjo in bi morali ravnati drug z drugim kakor bratje.
Bulgarian Всички хора се раждат свободни и равни по достойнство и права. Те са надарени с разум и съвест и следва да се отнасят помежду си в дух на братство.
Turkish Bütün insanlar hür, haysiyet ve haklar bakımından eşit doğarlar. Akıl ve vicdana sahiptirler ve birbirlerine karşı kardeşlik zihniyeti ile hareket etmelidirler.

See also[edit]

External links[edit]