Difference between revisions of "Languages of the Volga-Kama region"

From Apertium
Jump to navigation Jump to search
 
(7 intermediate revisions by 3 users not shown)
Line 31: Line 31:
 
|| [[HFST|HFST (lexc+twol)]]
 
|| [[HFST|HFST (lexc+twol)]]
 
|| development
 
|| development
|align="right"| {{#lst:Apertium-myv-fin/stats|myv-stems}}
+
|align="right"| {{#lst:Apertium-myv-fin/stats|myv_stems}}
 
|align="center"|
 
|align="center"|
 
|| [[apertium-myv-fin]] ([[incubator]])
 
|| [[apertium-myv-fin]] ([[incubator]])
Line 41: Line 41:
 
|| <code>tat</code>
 
|| <code>tat</code>
 
|| [[HFST|HFST (lexc+twol)]]
 
|| [[HFST|HFST (lexc+twol)]]
  +
|| {{#lst:Apertium-tat/stats|state}}
|| working
 
 
|align="right"| {{#lst:Apertium-tat/stats|stems}}
 
|align="right"| {{#lst:Apertium-tat/stats|stems}}
 
|align="center"| [[Apertium-tat#Current_State|~{{:Apertium-tat/stats/average}}%]]
 
|align="center"| [[Apertium-tat#Current_State|~{{:Apertium-tat/stats/average}}%]]
  +
|| {{#lst:Apertium-tat/stats|location}}
|| [[apertium-tat]] ([[languages]])
 
  +
|| {{#lst:Apertium-tat/stats|authors}}
|| [[User:Ilnar.salimzyan|Ilnar]], [[User:Francis Tyers|Fran]], [[User:Firespeaker|Jonathan]], Milli
 
 
|-
 
|-
 
| <code>[[apertium-chv]]</code>
 
| <code>[[apertium-chv]]</code>
Line 75: Line 75:
 
|| [[HFST|HFST (lexc+twol)]]
 
|| [[HFST|HFST (lexc+twol)]]
 
|| development
 
|| development
|align="right"| {{#lst:Apertium-mrj-fin/stats|mrj-stems}}
+
|align="right"| {{#lst:Apertium-mrj-fin/stats|mrj_stems}}
 
|align="center"|
 
|align="center"|
 
|| [[apertium-mrj-fin]] ([[incubator]])
 
|| [[apertium-mrj-fin]] ([[incubator]])
Line 86: Line 86:
 
|| [[HFST|HFST (lexc+twol)]]
 
|| [[HFST|HFST (lexc+twol)]]
 
|| prototype
 
|| prototype
|align="right"| {{#lst:Apertium-udm-rus/stats|udm-stems}}
+
|align="right"| {{#lst:Apertium-udm-rus/stats|udm_stems}}
 
|align="center"|
 
|align="center"|
 
|| [[apertium-udm-rus]]&nbsp;([[nursery]])
 
|| [[apertium-udm-rus]]&nbsp;([[nursery]])
Line 97: Line 97:
 
|| [[HFST|HFST (lexc+twol)]]
 
|| [[HFST|HFST (lexc+twol)]]
 
|| prototype
 
|| prototype
|align="right"| {{#lst:Apertium-kpv-mhr/stats|kpv-stems}}
+
|align="right"| {{#lst:Apertium-kpv-mhr/stats|kpv_stems}}
 
|align="center"|
 
|align="center"|
|| [[apertium-kpv-mhr]]&nbsp;([[incubator]]) <br> [[apertium-kpv-fin]]&nbsp;([[incubator]])
+
|| [[apertium-kpv-mhr]]&nbsp;([[incubator]])
 
|| [[User:Francis_Tyers|Fran]], [[User:Trondtr|Trond]], Fedina, Andrei Chemyshev
 
|| [[User:Francis_Tyers|Fran]], [[User:Trondtr|Trond]], Fedina, Andrei Chemyshev
 
|-
 
|-
Line 108: Line 108:
 
|| [[HFST|HFST (lexc+twol)]]
 
|| [[HFST|HFST (lexc+twol)]]
 
|| prototype
 
|| prototype
|align="right"| {{#lst:Apertium-kpv-mhr/stats|mhr-stems}}
+
|align="right"| {{#lst:Apertium-kpv-mhr/stats|mhr_stems}}
 
|align="center"|
 
|align="center"|
 
|| [[apertium-kpv-mhr]]&nbsp;([[incubator]])
 
|| [[apertium-kpv-mhr]]&nbsp;([[incubator]])
Line 118: Line 118:
 
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.
 
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"
+
{| style="text-align: center;" class="wikitable dixtable"
 
|- style="background: #ececec"
 
|- style="background: #ececec"
 
! !! tat !! chv !! bak !! mrj !! udm !! mhr !! myv !! kpv
 
! !! tat !! chv !! bak !! mrj !! udm !! mhr !! myv !! kpv
 
|-
 
|-
| '''tat''' || - || ''[[Apertium-cv-tt|cv-tt]]''<br>{{#lst:Apertium-cv-tt/stats|cv-tt-stems}} || ''[[Apertium-tat-bak|tat-bak]]''<br>{{#lst:Apertium-tat-bak/stats|tat-bak-stems}} || || || || ||
+
| '''tat''' || - || ''[[Apertium-chv-tat|chv-tat]]''<br>{{#lst:Apertium-chv-tat/stats|chv-tat_stems}} || [[Apertium-tat-bak|tat-bak]]<br>{{#lst:Apertium-tat-bak/stats|tat-bak_stems}} || || || || ||
 
|-
 
|-
| '''chv''' || ''[[Apertium-cv-tt|cv-tt]]''<br>{{#lst:Apertium-cv-tt/stats|cv-tt-stems}} || - || || || || || ||
+
| '''chv''' || ''[[Apertium-chv-tat|chv-tat]]''<br>{{#lst:Apertium-chv-tat/stats|chv-tat_stems}} || - || || || || || ||
 
|-
 
|-
| '''bak''' || ''[[Apertium-tat-bak|tat-bak]]''<br>{{#lst:Apertium-tat-bak/stats|tat-bak-stems}} || || - || || || || ||
+
| '''bak''' || [[Apertium-tat-bak|tat-bak]]<br>{{#lst:Apertium-tat-bak/stats|tat-bak_stems}} || || - || || || || ||
 
|-
 
|-
 
| '''mrj''' || || || || - || || || ||
 
| '''mrj''' || || || || - || || || ||
Line 132: Line 132:
 
| '''udm''' || || || || || - || || ||
 
| '''udm''' || || || || || - || || ||
 
|-
 
|-
| '''mhr''' || || || || || || - || || ''[[Apertium-kpv-mhr|kpv-mhr]]''<br>{{#lst:Apertium-kpv-mhr/stats|kpv-mhr-stems}}
+
| '''mhr''' || || || || || || - || || ''[[Apertium-kpv-mhr|kpv-mhr]]''<br>{{#lst:Apertium-kpv-mhr/stats|kpv-mhr_stems}}
 
|-
 
|-
 
| '''myv''' || || || || || || || - ||
 
| '''myv''' || || || || || || || - ||
 
|-
 
|-
| '''kpv''' || || || || || || ''[[Apertium-kpv-mhr|kpv-mhr]]''<br>{{#lst:Apertium-kpv-mhr/stats|kpv-mhr-stems}} || || -
+
| '''kpv''' || || || || || || ''[[Apertium-kpv-mhr|kpv-mhr]]''<br>{{#lst:Apertium-kpv-mhr/stats|kpv-mhr_stems}} || || -
 
|-
 
|-
 
| || || || || || || || ||
 
| || || || || || || || ||
 
|-
 
|-
| '''fin''' || || || || ''[[Apertium-mrj-fin|mrj-fin]]''<br>{{#lst:Apertium-mrj-fin/stats|mrj-fin-stems}} || ''[[Apertium-fin-udm|fin-udm]]''<br>{{#lst:Apertium-fin-udm/stats|fin-udm-stems}} || || ''[[Apertium-myv-fin|myv-fin]]''<br>{{#lst:Apertium-myv-fin/stats|myv-fin-stems}} || ''[[Apertium-kpv-fin|kpv-fin]]''<br>{{#lst:Apertium-kpv-fin/stats|kpv-fin-stems}}
+
| '''fin''' || || || || ''[[Apertium-mrj-fin|mrj-fin]]''<br>{{#lst:Apertium-mrj-fin/stats|mrj-fin_stems}} || ''[[Apertium-fin-udm|fin-udm]]''<br>{{#lst:Apertium-fin-udm/stats|fin-udm_stems}} || || ''[[Apertium-myv-fin|myv-fin]]''<br>{{#lst:Apertium-myv-fin/stats|myv-fin_stems}} || ''[[Apertium-kpv-fin|kpv-fin]]''<br>{{#lst:Apertium-kpv-fin/stats|kpv-fin_stems}}
 
|-
 
|-
| '''kaz''' || '''[[Apertium-kaz-tat|kaz-tat]]'''<br>{{#lst:Apertium-kaz-tat/stats|kaz-tat-stems}} || || || || || || ||
+
| '''kaz''' || '''[[Apertium-kaz-tat|kaz-tat]]'''<br>'''{{#lst:Apertium-kaz-tat/stats|kaz-tat_stems}}''' || || || || || || ||
 
|-
 
|-
| '''kir''' || ''[[Apertium-tat-kir|tat-kir]]''<br>{{#lst:Apertium-tat-kir/stats|tat-kir-stems}} || || || || || || ||
+
| '''kir''' || ''[[Apertium-tat-kir|tat-kir]]''<br>{{#lst:Apertium-tat-kir/stats|tat-kir_stems}} || || || || || || ||
 
|-
 
|-
| '''rus''' || ''[[Apertium-tt-ru|tt-ru]]''<br>{{#lst:Apertium-tt-ru/stats|tt-ru-stems}} || ''[[Apertium-cv-ru|cv-ru]]''<br>{{#lst:Apertium-cv-ru/stats|cv-ru-stems}} || || || ''[[Apertium-udm-rus|udm-rus]]''<br>{{#lst:Apertium-udm-rus/stats|udm-rus-stems}} || || ||
+
| '''rus''' || [[Apertium-tat-rus|tat-rus]]<br>{{#lst:Apertium-tat-rus/stats|tat-rus_stems}} || ''[[Apertium-cv-ru|cv-ru]]''<br>{{#lst:Apertium-cv-ru/stats|cv-ru_stems}} || || || [[Apertium-udm-rus|udm-rus]]<br>{{#lst:Apertium-udm-rus/stats|udm-rus_stems}} || || ||
 
|-
 
|-
| '''tur''' || ''[[Apertium-tur-tat|tur-tat]]''<br>{{#lst:Apertium-tur-tat/stats|tur-tat-stems}} || ''[[Apertium-cv-tr|cv-tr]]''<br>{{#lst:Apertium-cv-tr/stats|cv-tr-stems}} || || || || || ||
+
| '''tur''' || [[Apertium-tur-tat|tur-tat]]<br>{{#lst:Apertium-tur-tat/stats|tur-tat_stems}} || ''[[Apertium-cv-tr|cv-tr]]''<br>{{#lst:Apertium-cv-tr/stats|cv-tr_stems}} || || || || || ||
 
|}
 
|}
   

Latest revision as of 23:25, 22 December 2014

The languages of the Volga-Kama region include several Turkic and Uralic languages spoken in the Volga-Kama region (along the Volga and Kama rivers) in Russia. These include [varieties of] Tatar, Bashqort, Chuvash, Mari, Komi, Mordvin, and Udmurt (and linguistically, to some extent, Russian).

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 Volga-Kama 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 coverage location primary authors
-2 -3
apertium-myv Erzya myv HFST (lexc+twol) development 74,977 apertium-myv-fin (incubator) Fran, Jack Rueter
apertium-tat Tatar tt tat HFST (lexc+twol) production 55,702 ~91% apertium-tat (languages) Ilnar, Fran, Jonathan, Röstäm
apertium-chv Chuvash cv chv HFST (lexc+twol) development 8,579 ~85% apertium-chv (languages) Hèctor
apertium-bak Bashkir ba bak HFST (lexc+twol) development 2,827 ~66% apertium-bak (languages) Fran, Jonathan, Ilnar, Milli
apertium-mrj Hill Mari mrj HFST (lexc+twol) development 53,051 apertium-mrj-fin (incubator) Fran, kuprina, jackrueter
apertium-udm Udmurt udm HFST (lexc+twol) prototype 196 apertium-udm-rus (nursery) Fran, Trond, Andrey, Лукерья, Алексей
apertium-kpv Komi-Zyrian kpv HFST (lexc+twol) prototype 135 apertium-kpv-mhr (incubator) Fran, Trond, Fedina, Andrei Chemyshev
apertium-mhr Meadow Mari mhr HFST (lexc+twol) prototype 117 apertium-kpv-mhr (incubator) Fran, Fedina, Andrei Chemyshev

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.

tat chv bak mrj udm mhr myv kpv
tat - chv-tat
198
tat-bak
2,941
chv chv-tat
198
-
bak tat-bak
2,941
-
mrj -
udm -
mhr - kpv-mhr
127
myv -
kpv kpv-mhr
127
-
fin mrj-fin
273
fin-udm
93
myv-fin
401
kpv-fin
1
kaz 'kaz-tat
'
kir tat-kir
rus tat-rus
5,999
cv-ru
75
udm-rus
148
tur tur-tat
3,317
cv-tr
100

The languages[edit]

Volga-Kama languages by subgroup[edit]

Volga-Kama language vulnerability[edit]

The following table shows information about Volga-Kama varieties.

language iso num speakers UNESCO classification
Tatar tat 6500K 0. none
Bashqort bak 1379K 1. vulnerable
Chuvash chv 1325K 1. vulnerable
Udmurt udm 0464K 2. definitely endangered
Mari - Eastern mhr 0414K 2. definitely endangered
Mordvin - Erzya myv 0400K 2. definitely endangered
Komi - Zyryan kpv 0217K 2. definitely endangered
Mordvin - Moksha mdf 0200K 2. definitely endangered
Komi - Permyak koi 0094K 2. definitely endangered
Mari - Western mrj 0037K 3. severely endangered
Komi - Yazva koi 0000K 3. severely endangered

Existing general resources[edit]

Grammars[edit]

Dictionaries[edit]

Existing computational resources[edit]

Corpora and corpora projects[edit]

Spell-checkers[edit]

Text-to-speech and speech-to-text systems[edit]

Keyboards[edit]

  • Xkb includes keyboards for the following languages:
    • Tatar
    • Chuvash
    • ...?

Morphological Transducers[edit]

Scholarship[edit]