Difference between revisions of "North Saami and Lule Saami"
Jump to navigation
Jump to search
(→TODO) |
|||
| (10 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=== |
|||
* <s>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></s> |
|||
::Replaced > with → and < with ← |
|||
* Re-train the HMM-based POS tagger on a Sami corpus. |
|||
* Closed categories in sme analyser |
|||
; eará -- ietjá |
|||
==Reminders== |
|||
* 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== |
|||
;Analysing some Northern Sami text: |
|||
<pre> |
<pre> |
||
$ echo "eará" | osme |
|||
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \ |
|||
191480 0 |
|||
gii beare sáhttá čállit artihkkaliid." | lt-proc sme-smj.automorf.bin |
|||
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 |
|||
^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<A><Attr>/máŋggagielat<A><Sg><Nom>$ ^prošeakta/prošeakta<N><Sg><Nom>$ |
|||
ietjá+Pron+Indef+Attr ietjá+Pron+Indef+Attr +? |
|||
^man/man<ADV>/mii<Pron><Interr><Sg><Gen>/mii<Pron><Interr><Sg><Acc>/mii<Pron><Rel><Sg><Gen>/mii<Pron><Rel><Sg><Acc>$ ^ulbmilin/ulbmil<N><Ess>$ |
|||
^lea/leat<V><IV><Ind><Prs><Sg3>$ ^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>$ ^diehtosátnegirjji/diehtosátnegirji<N><Sg><Acc>$ |
|||
^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<Pron><Interr><Sg><Nom>/gii<Pron><Rel><Sg><Nom>$ ^beare/beare<ADV>$ ^sáhttá/sáhttit<V><IV><Ind><Prs><Sg3>$ |
|||
^čállit/čállit<V><TV><Inf>/čállit<V><TV><Ind><Prs><Pl1>$ ^artihkkaliid/artihkal<N><Pl><Gen>/artihkal<N><Pl><Acc>$. |
|||
</pre> |
</pre> |
||
;Disambiguating and annotating text with Constraint grammar: |
|||
;buot -- divnna |
|||
<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 | cg-proc sme-smj.rlx.bin |
|||
buot buot+Adv |
|||
buot buot+Pron+Indef |
|||
$ echo "divnna" | osmj |
|||
^Wikipedia/Wikipedia<N><Prop><Sg><Nom><@SUBJ→>$ ^lea/leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^máŋggagielat/máŋggagielat<A><Attr><@→N>$ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
^prošeakta/prošeakta<N><Sg><Nom><@←SPRED>$ ^man/mii<Pron><Rel><Sg><Gen><@→N>$ ^ulbmilin/ulbmil<N><Ess><@SPRED→>$ |
|||
divnna divnna+Pron+Indef+Sg+Nom |
|||
^lea/leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^ráhkadit/ráhkadit<V><TV><Inf><@-FMAINV>$ ^almmolaš/almmolaš<A><Attr><@→N>$ |
|||
divnna divnna+Pron+Indef+Attr |
|||
^diehtosátnegirjji/diehtosátnegirji<N><Sg><Acc><@←OBJ>$ ^gosa/gosa<ADV>$ ^gii/gii<Pron><Rel><Sg><Nom><@SUBJ→>$ ^beare/beare<ADV>$ |
|||
^sáhttá/sáhttit<V><IV><Ind><Prs><Sg3><@+FAUXV>$ ^čállit/čállit<V><TV><Inf><@-FMAINV>$ ^artihkkaliid/artihkal<N><Pl><Acc><@←OBJ>$. |
|||
</pre> |
</pre> |
||
; ieš#guhtet -- iesj#guhtik |
|||
;Finishing off the disambiguation with Apertium's HMM tagger: |
|||
<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 | apertium-tagger -g sme-smj.prob |
|||
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<N><Prop><Sg><Nom><@SUBJ→>$ ^leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^máŋggagielat<A><Attr><@→N>$ ^prošeakta<N><Sg><Nom><@←SPRED>$ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
^mii<Pron><Rel><Sg><Gen><@→N>$ ^ulbmil<N><Ess><@SPRED→>$ ^leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^ráhkadit<V><TV><Inf><@-FMAINV>$ |
|||
iesj#guhtik+Pron+Indef+Gen+Foc/ge iesj#guhtik+Pron+Indef+Gen+Foc/ge +? |
|||
^almmolaš<A><Attr><@→N>$ ^diehtosátnegirji<N><Sg><Acc><@←OBJ>$ ^gosa<ADV>$ ^gii<Pron><Rel><Sg><Nom><@SUBJ→>$ ^beare<ADV>$ |
|||
^sáhttit<V><IV><Ind><Prs><Sg3><@+FAUXV>$ ^čállit<V><TV><Inf><@-FMAINV>$ ^artihkal<N><Pl><Acc><@←OBJ>$. |
|||
$ 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 |
|||
;Applying lexical transfer and chunking: |
|||
<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 |
|||
apertium-transfer apertium-sme-smj.sme-smj.t1x sme-smj.t1x.bin sme-smj.autobil.bin |
|||
$ echo maid | osme |
|||
^nom<SN><@SUBJ→><Sg><Nom>{^Wikipedia<N><Prop><Sg><Nom>$}$ ^verb<SV><@+FMAINV>{^liehket<V><Ind><Prs><Sg3>$}$ ^nom<SN><@→N>{^@máŋggagielat<A><Attr>$}$ |
|||
0%>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>100% |
|||
^nom<SN><Sg><Nom>{^prosjækta<N><Sg><Nom>$}$ ^pronom<SN><@→N><Sg><Gen>{^mij<Pron><Rel><Sg><Gen>$}$ ^nom<SN><@SPRED→><Ess>{^ulmme<N><Ess>$}$ |
|||
maid mii+Pron+Interr+Pl+Acc |
|||
^verb<SV><@+FMAINV>{^liehket<V><Ind><Prs><Sg3>$}$ ^verb<SV><@-FMAINV>{^dahkat<V><Inf>$}$ ^nom<SN><@→N>{^almulasj<A><Attr>$}$ |
|||
maid mii+Pron+Interr+Pl+Gen |
|||
^nom<SN><@←OBJ><Sg><Acc>{^@diehtosátnegirji<N><Sg><Acc>$}$ ^adv<Adv>{^ADV><ADV>$}$ ^pronom<SN><@SUBJ→><Sg><Nom>{^guhti<Pron><Rel><Sg><Nom>$}$ |
|||
maid mii+Pron+Interr+Sg+Acc |
|||
^adv<Adv>{^beru<ADV>$}$ ^verb<SV>{^sáhttet<V><Ind><Prs><Sg3>$}$ ^verb<SV><@-FMAINV>{^tjállet<V><Inf>$}$ |
|||
maid mii+Pron+Rel+Pl+Acc |
|||
^nom<SN><@←OBJ><Pl><Acc>{^artihkal<N><Pl><Acc>$}$. |
|||
maid mii+Pron+Rel+Pl+Gen |
|||
maid mii+Pron+Rel+Sg+Acc |
|||
maid maid+Adv |
|||
maid maid+Interj |
|||
</pre> |
</pre> |
||
==Reminders== |
|||
; Running through the whole system |
|||
<pre> |
|||
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \ |
|||
gii beare sáhttá čállit artihkkaliid." | apertium -d . sme-smj |
|||
* In the transfer rule files, don't forget to escape the '+' character in tags, for example: |
|||
Wikipedia l @máŋggagielat prosjækta man ulmmen l dahkat almulasj @diehtosátnegirji #ADV> |
|||
::'''no:''' <code><attr-item tags="@+FMAINV"/></code> , |
|||
guhti beru sáhttá tjállet artihkkalijt |
|||
::'''yes:''' <code><attr-item tags="@\+FMAINV"/></code> |
|||
==Testing== |
|||
<pre> |
|||
$ 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. |
|||
</pre> |
</pre> |
||
| Line 98: | Line 101: | ||
*[[/Regression tests]] |
*[[/Regression tests]] |
||
*[[/Pending tests]] |
|||
==External links== |
==External links== |
||
| Line 103: | 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.
