Difference between revisions of "North Saami and Lule Saami"
Jump to navigation
Jump to search
(→TODO) |
|||
| (16 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
{{TOCD}} |
{{TOCD}} |
||
This page gives some details about the North Sámi to Lule Sámi translator. |
|||
==Files== |
|||
==Standardisation== |
|||
*<code>apertium-sme-smj.sme.dix</code> — Northern Sami transducer |
|||
*<code>apertium-sme-smj.sme-smj.dix</code> — Transfer lexicon |
|||
* Leahppi go gávdnan gusade? |
|||
*<code>apertium-sme-smj.smj.dix</code> — Lule Sami transducer |
|||
** Læhppe gu gávnnam gusáda? |
|||
*<code>apertium-sme-smj.sme-smj.rlx</code> — Constraint grammar |
|||
** Lihppe gu gávnnam gusáda? |
|||
*<code>apertium-sme-smj.sme-smj.t1x</code> — Transfer rule file (level 1 -- Local re-ordering, chunking) |
|||
*<code>apertium-sme-smj.sme-smj.t2x</code> — Transfer rule file (level 2 -- Phrase and chunk re-ordering) |
|||
*<code>apertium-sme-smj.sme-smj.t3x</code> — Transfer rule file (level 3 -- Final touches) |
|||
==TODO== |
==TODO== |
||
===Tagset mismatches=== |
|||
* Mapped tags in the CG use special characters in Apertium, for example '>' (used for delimiting tags) and '-' (causes problems with pretransfer). These should be replaced somehow. |
|||
::Example: |
|||
:::<code>^Wikipedia<N><Prop><Sg><Nom><@SUBJ>>$</code> or <code>^prošeakta<N><Sg><Nom><@<SPRED>$</code> |
|||
:::This comes from the CG tag @SUBJ> |
|||
* Re-train the HMM-based POS tagger on a Sami corpus. |
|||
* Closed categories in sme analyser |
|||
; eará -- ietjá |
|||
==Reminders== |
|||
<pre> |
|||
* In the transfer rule files, don't forget to escape the '+' character in tags, for example: |
|||
$ echo "eará" | osme |
|||
::'''no:''' <code><attr-item tags="@+FMAINV"/></code> , |
|||
191480 0 |
|||
::'''yes:''' <code><attr-item tags="@\+FMAINV"/></code> |
|||
eará eará+Pron+Indef+Sg+Nom |
|||
eará eará+Pron+Indef+Sg+Gen |
|||
eará eará+Pron+Indef+Sg+Acc |
|||
eará eará+Pron+Indef+Attr |
|||
$ echo "ietjá+Pron+Indef+Attr" | dsmj |
|||
==Testing== |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
ietjá+Pron+Indef+Attr ietjá+Pron+Indef+Attr +? |
|||
</pre> |
|||
;buot -- divnna |
|||
;Analysing some Northern Sami text: |
|||
<pre> |
<pre> |
||
$ echo "buot" | osme |
|||
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
gii beare sáhttá čállit artihkkaliid." | lt-proc sme-smj.automorf.bin |
|||
buot buot+Adv |
|||
buot buot+Pron+Indef |
|||
$ echo "divnna" | osmj |
|||
^Wikipedia/Wikipedia<N><Prop><Sg><Nom>/Wikipedia<N><Prop><Sg><Gen>/Wikipedia<N><Prop><Sg><Acc>$ ^lea/leat<V><IV><Ind><Prs><Sg3>$ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
^máŋggagielat/*máŋggagielat$ ^prošeakta/prošeakta<N><Sg><Nom>$ ^man/man<ADV>$ ^ulbmilin/*ulbmilin$ ^lea/leat<V><IV><Ind><Prs><Sg3>$ |
|||
divnna divnna+Pron+Indef+Sg+Nom |
|||
^ráhkadit/ráhkadit<V><TV><Inf>/ráhkadit<V><TV><Ind><Prs><Pl3>/ráhkadit<V><TV><Ind><Prt><Sg2>$ ^almmolaš/almmolaš<A><Attr>/almmolaš<A><Sg><Nom>$ |
|||
divnna divnna+Pron+Indef+Attr |
|||
^diehtosátnegirjji/*diehtosátnegirjji$ |
|||
^gosa/gosa<ADV>/gossat<V><IV><VGen>/gossat<V><IV><Imprt><Prs><ConNeg>/gossat<V><IV><Imprt><Prs><Sg2>/gossat<V><IV><Ind><Prs><ConNeg>$ ^gii/*gii$ |
|||
^beare/beare<ADV>$ ^sáhttá/sáhttit<V><IV><Ind><Prs><Sg3>$ ^čállit/čállit<V><TV><Inf>/čállit<V><TV><Ind><Prs><Pl1>$ ^artihkkaliid/*artihkkaliid$. |
|||
</pre> |
</pre> |
||
; ieš#guhtet -- iesj#guhtik |
|||
;Disambiguating and annotating text with Constraint grammar: |
|||
<pre> |
<pre> |
||
$ echo "iešguđetge" | osme |
|||
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
gii beare sáhttá čállit artihkkaliid." | lt-proc sme-smj.automorf.bin | cg-proc sme-smj.rlx.bin |
|||
iešguđetge ieš#guhtege+Pron+Indef+Pl+Nom |
|||
iešguđetge ieš#guhtet+Pron+Indef+Acc+Foc/ge |
|||
iešguđetge ieš#guhtet+Pron+Indef+Gen+Foc/ge |
|||
iešguđetge ieš#guđet+Pron+Indef+Foc/ge |
|||
$ echo "iesj#guhtik+Pron+Indef+Gen+Foc/ge" | dsmj |
|||
^Wikipedia/Wikipedia<N><Prop><Sg><Nom><@SUBJ%>$ ^lea/leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^máŋggagielat/*máŋggagielat$ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
^prošeakta/prošeakta<N><Sg><Nom><@<SPRED>$ ^man/man<ADV>$ ^ulbmilin/*ulbmilin$ ^lea/leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ |
|||
iesj#guhtik+Pron+Indef+Gen+Foc/ge iesj#guhtik+Pron+Indef+Gen+Foc/ge +? |
|||
^ráhkadit/ráhkadit<V><TV><Inf><@-FMAINV>$ ^almmolaš/almmolaš<A><Sg><Nom><@%SUBJ>$ ^diehtosátnegirjji/*diehtosátnegirjji$ ^gosa/gosa<ADV>$ ^gii/*gii$ |
|||
^beare/beare<ADV>$ ^sáhttá/sáhttit<V><IV><Ind><Prs><Sg3><@+FAUXV>$ ^čállit/čállit<V><TV><Inf><@-FMAINV>$ ^artihkkaliid/*artihkkaliid$ |
|||
$ echo "iesj#guhtik+Pron+Indef+Foc/ge" | dsmj |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
iesj#guhtik+Pron+Indef+Foc/ge iesj#guhtik#ge |
|||
iesj#guhtik+Pron+Indef+Foc/ge iesj#guhtikge |
|||
iesj#guhtik+Pron+Indef+Foc/ge iesjguhtik#ge |
|||
iesj#guhtik+Pron+Indef+Foc/ge iesjguhtikge |
|||
</pre> |
</pre> |
||
; maid -- aj |
|||
;Finishing off the disambiguation with Apertium's HMM tagger: |
|||
<pre> |
<pre> |
||
$ echo aj | osmj |
|||
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
gii beare sáhttá čállit artihkkaliid." | lt-proc sme-smj.automorf.bin | cg-proc sme-smj.rlx.bin | apertium-tagger -g sme-smj.prob |
|||
aj aj+Pcle |
|||
$ echo maid | osme |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
maid mii+Pron+Interr+Pl+Acc |
|||
maid mii+Pron+Interr+Pl+Gen |
|||
maid mii+Pron+Interr+Sg+Acc |
|||
maid mii+Pron+Rel+Pl+Acc |
|||
maid mii+Pron+Rel+Pl+Gen |
|||
maid mii+Pron+Rel+Sg+Acc |
|||
maid maid+Adv |
|||
maid maid+Interj |
|||
^Wikipedia<N><Prop><Sg><Nom><@SUBJ%>$ ^leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^*máŋggagielat$ ^prošeakta<N><Sg><Nom><@<SPRED>$ ^man<ADV>$ |
|||
^*ulbmilin$ ^leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^ráhkadit<V><TV><Inf><@-FMAINV>$ ^almmolaš<A><Sg><Nom><@%SUBJ>$ ^*diehtosátnegirjji$ |
|||
^gosa<ADV>$ ^*gii$ ^beare<ADV>$ ^sáhttit<V><IV><Ind><Prs><Sg3><@+FAUXV>$ ^čállit<V><TV><Inf><@-FMAINV>$ ^*artihkkaliid$ |
|||
</pre> |
</pre> |
||
==Reminders== |
|||
;Applying lexical transfer and chunking: |
|||
* In the transfer rule files, don't forget to escape the '+' character in tags, for example: |
|||
::'''no:''' <code><attr-item tags="@+FMAINV"/></code> , |
|||
::'''yes:''' <code><attr-item tags="@\+FMAINV"/></code> |
|||
==Testing== |
|||
<pre> |
<pre> |
||
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji |
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji \ |
||
gii beare sáhttá čállit artihkkaliid." | |
gosa gii beare sáhttá čállit artihkkaliid." | apertium -d . sme-smj |
||
Wikipedia la moattegielak prosjækta/prosjäkta #mij ulmmen la dahkat almulasj #diehtobáhkogirjje |
|||
apertium-transfer apertium-sme-smj.sme-smj.t1x sme-smj.t1x.bin sme-smj.autobil.bin |
|||
#masi guhti beru máhttá tjállet artihkkalijt. |
|||
</pre> |
|||
==See also== |
|||
^nom<SN><@SUBJ%><Sg><Nom>{^Wikipedia<N><Prop><Sg><Nom>$}$ ^default{^liehket<V><IV><Ind><Prs><Sg3><@+FMAINV>$}$ ^unknown{^*máŋggagielat$}$ |
|||
^nom<SN><Sg><Nom>{^prosjækta<N><Sg><Nom>$}$ ^default{^man<ADV>$}$ ^default{^@ulbmil<N><Ess><@SPRED>>$}$ |
|||
^default{^liehket<V><IV><Ind><Prs><Sg3><@+FMAINV>$}$ ^default{^dahkat<V><TV><Inf><@-FMAINV>$}$ ^default{^almulasj<A><Sg><Nom><@%SUBJ>$}$ |
|||
^unknown{^*diehtosátnegirjji$}$ ^default{^<ADV>$}$ ^unknown{^*gii$}$ ^default{^@beare<ADV>$}$ ^default{^sáhttet<V><IV><Ind><Prs><Sg3><@+FAUXV>$}$ |
|||
^default{^tjállet<V><TV><Inf><@-FMAINV>$}$ ^unknown{^*artihkkaliid$}$. |
|||
*[[/Regression tests]] |
|||
</pre> |
|||
*[[/Pending tests]] |
|||
==External links== |
==External links== |
||
| Line 84: | Line 107: | ||
* [http://www.divvun.no/doc/lang/sme/docu-sme-grammartags.html Northern Sami: The grammatical tags] |
* [http://www.divvun.no/doc/lang/sme/docu-sme-grammartags.html Northern Sami: The grammatical tags] |
||
[[Category: |
[[Category:Northern Sámi and Lule Sámi]] |
||
Revision as of 14:22, 17 June 2010
This page gives some details about the North Sámi to Lule Sámi translator.
Standardisation
- Leahppi go gávdnan gusade?
- Læhppe gu gávnnam gusáda?
- Lihppe gu gávnnam gusáda?
TODO
Tagset mismatches
- eará -- ietjá
$ echo "eará" | osme 191480 0 eará eará+Pron+Indef+Sg+Nom eará eará+Pron+Indef+Sg+Gen eará eará+Pron+Indef+Sg+Acc eará eará+Pron+Indef+Attr $ echo "ietjá+Pron+Indef+Attr" | dsmj 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% ietjá+Pron+Indef+Attr ietjá+Pron+Indef+Attr +?
- buot -- divnna
$ echo "buot" | osme 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% buot buot+Adv buot buot+Pron+Indef $ echo "divnna" | osmj 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% divnna divnna+Pron+Indef+Sg+Nom divnna divnna+Pron+Indef+Attr
- ieš#guhtet -- iesj#guhtik
$ echo "iešguđetge" | osme 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% iešguđetge ieš#guhtege+Pron+Indef+Pl+Nom iešguđetge ieš#guhtet+Pron+Indef+Acc+Foc/ge iešguđetge ieš#guhtet+Pron+Indef+Gen+Foc/ge iešguđetge ieš#guđet+Pron+Indef+Foc/ge $ echo "iesj#guhtik+Pron+Indef+Gen+Foc/ge" | dsmj 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% iesj#guhtik+Pron+Indef+Gen+Foc/ge iesj#guhtik+Pron+Indef+Gen+Foc/ge +? $ echo "iesj#guhtik+Pron+Indef+Foc/ge" | dsmj 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% iesj#guhtik+Pron+Indef+Foc/ge iesj#guhtik#ge iesj#guhtik+Pron+Indef+Foc/ge iesj#guhtikge iesj#guhtik+Pron+Indef+Foc/ge iesjguhtik#ge iesj#guhtik+Pron+Indef+Foc/ge iesjguhtikge
- maid -- aj
$ echo aj | osmj 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% aj aj+Pcle $ echo maid | osme 0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% maid mii+Pron+Interr+Pl+Acc maid mii+Pron+Interr+Pl+Gen maid mii+Pron+Interr+Sg+Acc maid mii+Pron+Rel+Pl+Acc maid mii+Pron+Rel+Pl+Gen maid mii+Pron+Rel+Sg+Acc maid maid+Adv maid maid+Interj
Reminders
- In the transfer rule files, don't forget to escape the '+' character in tags, for example:
- no:
<attr-item tags="@+FMAINV"/>, - yes:
<attr-item tags="@\+FMAINV"/>
- no:
Testing
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji \ gosa gii beare sáhttá čállit artihkkaliid." | apertium -d . sme-smj Wikipedia la moattegielak prosjækta/prosjäkta #mij ulmmen la dahkat almulasj #diehtobáhkogirjje #masi guhti beru máhttá tjállet artihkkalijt.
