Difference between revisions of "Indic languages"

From Apertium
Jump to navigation Jump to search
Line 123: Line 123:


=== Existing language pairs ===
=== Existing language pairs ===
Text in ''italics'' denotes language pairs in the incubator. Regular text denotes a developing language pair in nursery, while text in '''bold''' denotes a stable well-working language pair in trunk and text in '''''bold and italics''''' denotes a pair in staging. Bidix stems as counted with [[dixcounter]] are displayed below.

==== Indic-Indic pairs ====



{| style="text-align: center;" class="wikitable"
{| style="text-align: center;" class="wikitable"
|- style="background: #ececec"
|- style="background: #ececec"
! !! hin !! ben !! urd !! san !! nep !! mar !! pan
! !! hin !! ben !! urd !! san !! nep !! mar !! pan
|-
|-
| '''hin''' || - || ''[[Apertium-bn-hi|bn-hi]]''<br>{{#lst:Apertium-bn-hi/stats|bn-hi-stems}} || [[Apertium-ur-hi|ur-hi]]<br>{{#lst:Apertium-ur-hi/stats|ur-hi-stems}} || || || ''[[Apertium-mr-hi|mr-hi]]''<br>{{#lst:Apertium-mr-hi/stats|mr-hi-stems}} || ''[[Apertium-pa-hi|pa-hi]]''<br>{{#lst:Apertium-pa-hi/stats|pa-hi-stems}}
| '''hin''' || - || || || || || ||
|-
|-
| '''ben''' || [[bn-hi]] || - || || || || ||
| '''ben''' || ''[[Apertium-bn-hi|bn-hi]]''<br>{{#lst:Apertium-bn-hi/stats|bn-hi-stems}} || - || || || || ||
|-
|-
| '''urd''' || [[ur-hi]] || || - || || || || [[ur-pa]]
| '''urd''' || [[Apertium-ur-hi|ur-hi]]<br>{{#lst:Apertium-ur-hi/stats|ur-hi-stems}} || || - || || || || ''[[Apertium-ur-pa|ur-pa]]''<br>{{#lst:Apertium-ur-pa/stats|ur-pa-stems}}
|-
|-
| '''san''' || || || || - || || ||
| '''san''' || || || || - || || ||
|-
|-
| '''nep''' || || || || || - || ||
| '''nep''' || || || || || - || ||
|-
| '''mar''' || [[mr-hi]] || || || || || - ||
|-
| '''pan''' || [[pa-hi]] || || || || || || -
|}

==== Pairs with non-Indic languages ====
{| style="text-align: center;" class="wikitable"
|- style="background: #ececec"
! !! eng !! asm !! epo !! pes
|-
|-
| '''hin''' || [[eng-hin]] || [[as-hi]] || ||
| '''mar''' || ''[[Apertium-mr-hi|mr-hi]]''<br>{{#lst:Apertium-mr-hi/stats|mr-hi-stems}} || || || || || - ||
|-
|-
| '''pan''' || ''[[Apertium-pa-hi|pa-hi]]''<br>{{#lst:Apertium-pa-hi/stats|pa-hi-stems}} || || ''[[Apertium-ur-pa|ur-pa]]''<br>{{#lst:Apertium-ur-pa/stats|ur-pa-stems}} || || || || -
| '''ben''' || [[bn-en]] || || ||
|-
|-
| '''urd''' || || || || [[ur-fa]]
| || || || || || || ||
|-
|-
| '''san''' || || || ||
| '''asm''' || ''[[Apertium-as-hi|as-hi]]''<br>{{#lst:Apertium-as-hi/stats|as-hi-stems}} || || || || || ||
|-
|-
| '''eng''' || [[Apertium-eng-hin|eng-hin]]<br>{{#lst:Apertium-eng-hin/stats|eng-hin-stems}} || ''[[Apertium-bn-en|bn-en]]''<br>{{#lst:Apertium-bn-en/stats|bn-en-stems}} || || || ''[[Apertium-ne-en|ne-en]]''<br>{{#lst:Apertium-ne-en/stats|ne-en-stems}} || ''[[Apertium-mar-eng|mar-eng]]''<br>{{#lst:Apertium-mar-eng/stats|mar-eng-stems}} ||
| '''nep''' || [[ne-en]] || || [[eo-ne]] ||
|-
|-
| '''mar''' || [[mar-eng]] || || ||
| '''epo''' || || || || || ''[[Apertium-eo-ne|eo-ne]]''<br>{{#lst:Apertium-eo-ne/stats|eo-ne-stems}} || ||
|-
|-
| '''pan''' || || || ||
| '''fas''' || || || ''[[Apertium-ur-fa|ur-fa]]''<br>{{#lst:Apertium-ur-fa/stats|ur-fa-stems}} || || || ||
|}
|}



Revision as of 07:59, 5 January 2014

The Indic languages include Hindi, Urdu, Bengali, Sanskrit, and a number of other languages. These languages are the dominant language family of the Indian subcontinent. The number of people that speak an Indic language is upwards of 900,000,000.

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 Indic 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 coverage location primary authors
-2 -3
apertium-san Sanskrit sa san lttoolbox working 123,373 - apertium-san (languages) Amba Kulkarni
apertium-hin Hindi hi hin lttoolbox working 37,833 ~83.1% apertium-hin (languages) Nikant, Abu Zaher Md. Faridee, Fran
apertium-ben Bengali bn ben lttoolbox development 8,230 ~74% apertium-ben (languages) Abu Zaher Md. Faridee
apertium-urd Urdu ur urd lttoolbox development 14,943 ~64.6% apertium-urd (languages) Muhammad Humayoun
apertium-nep Nepali ne nep lttoolbox prototype 215 - apertium-ne-en (incubator)
apertium-eo-ne (incubator)
apertium-mar Marathi mr mar lttoolbox prototype 14,886 - apertium-mar-eng (incubator)
apertium-mr-hi (incubator)
apertium-pan Punjabi pa pan possibly non-existant - - apertium-pa-hi (incubator)
apertium-ur-pa (incubator)

Indic Language Classification


Existing language pairs

Text in italics denotes language pairs in the incubator. Regular text denotes a developing language pair in nursery, while text in bold denotes a stable well-working language pair in trunk and text in bold and italics denotes a pair in staging. Bidix stems as counted with dixcounter are displayed below.

hin ben urd san nep mar pan
hin - bn-hi
ur-hi
mr-hi
pa-hi
ben bn-hi
-
urd ur-hi
- ur-pa
san -
nep -
mar mr-hi
-
pan pa-hi
ur-pa
-
asm as-hi
eng eng-hin
bn-en
ne-en
mar-eng
epo eo-ne
fas ur-fa

Tagset

Rough guide to tagsets in various Indic language transducers, with an eye to keeping stuff that is basically the same tagged the same (see also the general tagset list).

Phenomenon Morphology Description Tag(s) Language(s) Notes
Part of speech
Noun <n>