Difference between revisions of "Scandinavian MT project"

From Apertium
Jump to navigation Jump to search
 
(12 intermediate revisions by 2 users not shown)
Line 3: Line 3:
* https://meta.wikimedia.org/wiki/Grants:IEG/Pan-Scandinavian_Machine-assisted_Content_Translation
* https://meta.wikimedia.org/wiki/Grants:IEG/Pan-Scandinavian_Machine-assisted_Content_Translation


* https://meta.wikimedia.org/wiki/Skanwiki/Tinget
* https://meta.wikimedia.org/wiki/Skanwiki/Tinget / https://meta.wikimedia.org/wiki/Skanwiki/Skanwikiprojekt_MT

* http://blog.wikimedia.org/2016/06/01/scandinavian-wikipedias-content-translation/ / http://blogg.wikimedia.no/2015/12/14/verktoy-for-tverrskandinavisk-maskinomsetjing/


* [[North Germanic languages]]
* [[North Germanic languages]]
Line 9: Line 11:


==Status==
==Status==

Note: UDHR was probably used during development on on nno/nob stuff.


{|class=wikitable
{|class=wikitable
! Direction !! Pair !! Bidix !! Coverage !! Testvoc !! Release date !! Released !! WER (-u)
! Direction !! Pair !! Bidix !! Coverage<br/>UDHR – Wiki !! Testvoc !! Release date !! Released !! WER (-u)
|-
|-
| nob-nno || [[apertium-nno-nob|nno-nob]] || 69,305 || || ✓ || ||✓ || 10.71 %<ref>[[Apertium-nno-nob#WER-test_28.2F8_2009]]</ref>
| nob-nno || [[apertium-nno-nob|nno-nob]] ||69,397 || 99.2% – 92.6% || || ||✓ || 10.71 %<ref>[[Apertium-nno-nob#WER-test_28.2F8_2009]]</ref>
|-
|-
| nno-nob || [[apertium-nno-nob|nno-nob]] ||69,305 || || ✓ || || ✓ ||
| nno-nob || [[apertium-nno-nob|nno-nob]] ||69,397 || 98.9% – 90.6% || || || ✓ ||
|-
|-
| dan-nob || [[apertium-dan-nor|dan-nor]] || 49,063 || || ✓ || {{sc|1 februar 2016}} || ✓ || 10.87 %<ref>https://svn.code.sf.net/p/apertium/svn/trunk/apertium-dan-nor/WER/</ref>
| dan-nob || [[apertium-dan-nor|dan-nor]] ||53,746 || 95.9% – 88.1% || ✓ || {{sc|1 februar 2016}} || ✓ || 10.87 %<ref>https://svn.code.sf.net/p/apertium/svn/trunk/apertium-dan-nor/WER/</ref>
|-
|-
| dan-nno || [[apertium-dan-nor|dan-nor]] ||48,425 || || ✓ || {{sc|1 januar 2016}} || ✓ || 13.64 %, 22.64 %<ref>https://svn.code.sf.net/p/apertium/svn/trunk/apertium-dan-nor/WER/</ref>
| dan-nno || [[apertium-dan-nor|dan-nor]] ||53,746 || 92.7% – 87.3% || ✓ || {{sc|1 januar 2016}} || ✓ || 13.64 %, 22.64 %<ref>https://svn.code.sf.net/p/apertium/svn/trunk/apertium-dan-nor/WER/</ref>
|-
|-
| nob-dan || [[apertium-dan-nor|dan-nor]] ||49,063 || || ✓ || ||✓ ||
| nob-dan || [[apertium-dan-nor|dan-nor]] ||53,746 || 98.6% – 91.7% || ✓ || ||✓ ||
|-
|-
| nno-dan || [[apertium-dan-nor|dan-nor]] ||48,425 || || ✓ || {{sc|1 april 2016}} || ||
| nno-dan || [[apertium-dan-nor|dan-nor]] ||53,746 || 97.4% – 89.8% || ✓ || {{sc|1 april 2016}} || ✓ ||
|-
|-
| swe-nob || [[apertium-swe-nor|swe-nor]] || 7,786 || || || {{sc|17 mai 2016}} || ||
| swe-nob || [[apertium-swe-nor|swe-nor]] || 8,920 || 94.8% – 87.3% || || {{sc|17 mai 2016}} || ✓ ||
|-
|-
| swe-nno || [[apertium-swe-nor|swe-nor]] ||7,745 || || || {{sc|17 mai 2016}} || ||
| swe-nno || [[apertium-swe-nor|swe-nor]] || 8,920 || 93.8% – 87.0% || || {{sc|17 mai 2016}} || ✓ ||
|-
|-
| nob-swe || [[apertium-swe-nor|swe-nor]] ||7,786 || || || {{sc|17 mai 2016}} || ||
| nob-swe || [[apertium-swe-nor|swe-nor]] || 8,920 || 97.1% – 89.7% || || {{sc|17 mai 2016}} || ✓ ||
|-
|-
| nno-swe || [[apertium-swe-nor|swe-nor]] ||7,745 || || || {{sc|17 mai 2016}} || ||
| nno-swe || [[apertium-swe-nor|swe-nor]] || 8,920 || 96.6% – 87.4% || || {{sc|17 mai 2016}} || ✓ ||
|-
|-
| swe-dan || [[apertium-swe-dan|swe-dan]] || 8,283 || || || || ✓ || 31 %<ref>[[Apertium-swe-dan#Dansk_.28english_version_below.29]]</ref>
| swe-dan || [[apertium-swe-dan|swe-dan]] || 17,551 || 88.0% – 83.7% || || {{sc|1 mars 2016}} || ✓ || 31 %<ref>[[Apertium-swe-dan#Dansk_.28english_version_below.29]]</ref>
|-
|-
| dan-swe || [[apertium-swe-dan|swe-dan]] ||8,283 || || || {{sc|1 mars 2016}} || ||
| dan-swe || [[apertium-swe-dan|swe-dan]] ||17,551 || 90.4% – 82.9% || || {{sc|1 mars 2016}} || ✓ ||
|-
|-
|}
|}


===Stats from stemcounterbot===
===Stats from stemcounterbot===
(bidix stems buggy for swe-pairs)


{|class=wikitable
{|class=wikitable
Line 54: Line 57:
|-
|-
|}
|}

==Evaluation==

* [[Swedish]]: [https://svn.code.sf.net/p/apertium/svn/languages/apertium-swe/texts/kalmar.txt kalmar.txt] (1119 tokens)
* [[Danish]]: [https://svn.code.sf.net/p/apertium/svn/languages/apertium-dan/texts/venedig.txt venedig.txt] (1363 tokens)
* [[Norwegian Nynorsk]]:
* [[Norwegian Bokmål]]:


==Notes==
==Notes==

Latest revision as of 07:02, 28 June 2016



Status[edit]

Note: UDHR was probably used during development on on nno/nob stuff.

Direction Pair Bidix Coverage
UDHR – Wiki		 Testvoc Release date Released WER (-u)
nob-nno nno-nob 69,397 99.2% – 92.6% ✓ 10.71 %[1]
nno-nob nno-nob 69,397 98.9% – 90.6% ✓
dan-nob dan-nor 53,746 95.9% – 88.1% ✓ 1 februar 2016 ✓ 10.87 %[2]
dan-nno dan-nor 53,746 92.7% – 87.3% ✓ 1 januar 2016 ✓ 13.64 %, 22.64 %[3]
nob-dan dan-nor 53,746 98.6% – 91.7% ✓ ✓
nno-dan dan-nor 53,746 97.4% – 89.8% ✓ 1 april 2016 ✓
swe-nob swe-nor 8,920 94.8% – 87.3% 17 mai 2016 ✓
swe-nno swe-nor 8,920 93.8% – 87.0% 17 mai 2016 ✓
nob-swe swe-nor 8,920 97.1% – 89.7% 17 mai 2016 ✓
nno-swe swe-nor 8,920 96.6% – 87.4% 17 mai 2016 ✓
swe-dan swe-dan 17,551 88.0% – 83.7% 1 mars 2016 ✓ 31 %[4]
dan-swe swe-dan 17,551 90.4% – 82.9% 1 mars 2016 ✓

Stats from stemcounterbot[edit]

Pair Bidix t1x rules lrx rules
nno-nob 69,479 nno→nob: 22, nob→nno: 85 nno→nob: , nob→nno:
dan-nor 54,742 dan→nno: 31, dan→nob: 24, nor→dan: 22 dan→nno: , dan→nob: , nor→dan:
swe-nor 66,856 swe→nno: 30, swe→nob: 26, nor→swe: 27 swe→nno: , swe→nob: , nor→swe:
swe-dan 21,791 swe→dan: 24, dan→swe: 26 swe→dan: , dan→swe:

Evaluation[edit]

Notes[edit]

  1. ↑ Apertium-nno-nob#WER-test_28.2F8_2009
  2. ↑ https://svn.code.sf.net/p/apertium/svn/trunk/apertium-dan-nor/WER/
  3. ↑ https://svn.code.sf.net/p/apertium/svn/trunk/apertium-dan-nor/WER/
  4. ↑ Apertium-swe-dan#Dansk_.28english_version_below.29
Retrieved from "https://wiki.apertium.org/w/index.php?title=Scandinavian_MT_project&oldid=59038"