Difference between revisions of "North Saami and Lule Saami"

From Apertium
Jump to navigation Jump to search
(No difference)

Revision as of 07:17, 7 April 2009

Files

  • apertium-sme-smj.sme.dix — Northern Sami transducer
  • apertium-sme-smj.sme-smj.dix — Transfer lexicon
  • apertium-sme-smj.smj.dix — Lule Sami transducer
  • apertium-sme-smj.sme-smj.rlx — Constraint grammar
  • apertium-sme-smj.sme-smj.t1x — Transfer rule file (level 1 -- Local re-ordering, chunking)
  • apertium-sme-smj.sme-smj.t2x — Transfer rule file (level 2 -- Phrase and chunk re-ordering)
  • apertium-sme-smj.sme-smj.t3x — Transfer rule file (level 3 -- Final touches)

TODO

  • 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:
^Wikipedia<N><Prop><Sg><Nom><@SUBJ>>$ or ^prošeakta<N><Sg><Nom><@<SPRED>$
This comes from the CG tag @SUBJ>
Replaced > with → and < with ←
  • Re-train the HMM-based POS tagger on a Sami corpus.
  • Closed categories in sme analyser

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"/>

Testing

Analysing some Northern Sami text
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \
gii beare sáhttá čállit artihkkaliid." |  lt-proc sme-smj.automorf.bin

^Wikipedia/Wikipedia<N><Prop><Sg><Nom>/Wikipedia<N><Prop><Sg><Gen>/Wikipedia<N><Prop><Sg><Acc>$ ^lea/leat<V><IV><Ind><Prs><Sg3>$ 
^máŋggagielat/máŋggagielat<A><Attr>/máŋggagielat<A><Sg><Nom>$ ^prošeakta/prošeakta<N><Sg><Nom>$ 
^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>$.
Disambiguating and annotating text with Constraint grammar
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \ 
gii beare sáhttá čállit artihkkaliid." | lt-proc sme-smj.automorf.bin | cg-proc sme-smj.rlx.bin 

^Wikipedia/Wikipedia<N><Prop><Sg><Nom><@SUBJ→>$ ^lea/leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^máŋggagielat/máŋggagielat<A><Attr><@→N>$ 
^prošeakta/prošeakta<N><Sg><Nom><@←SPRED>$ ^man/mii<Pron><Rel><Sg><Gen><@→N>$ ^ulbmilin/ulbmil<N><Ess><@SPRED→>$ 
^lea/leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^ráhkadit/ráhkadit<V><TV><Inf><@-FMAINV>$ ^almmolaš/almmolaš<A><Attr><@→N>$ 
^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>$.
Finishing off the disambiguation with Apertium's HMM tagger
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \ 
gii beare sáhttá čállit artihkkaliid." |  lt-proc sme-smj.automorf.bin | cg-proc sme-smj.rlx.bin | apertium-tagger -g sme-smj.prob 

^Wikipedia<N><Prop><Sg><Nom><@SUBJ→>$ ^leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^máŋggagielat<A><Attr><@→N>$ ^prošeakta<N><Sg><Nom><@←SPRED>$ 
^mii<Pron><Rel><Sg><Gen><@→N>$ ^ulbmil<N><Ess><@SPRED→>$ ^leat<V><IV><Ind><Prs><Sg3><@+FMAINV>$ ^ráhkadit<V><TV><Inf><@-FMAINV>$ 
^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>$.

Applying lexical transfer and chunking
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \
gii beare sáhttá čállit artihkkaliid." |  lt-proc sme-smj.automorf.bin | cg-proc sme-smj.rlx.bin | apertium-tagger -g sme-smj.prob | \
apertium-transfer apertium-sme-smj.sme-smj.t1x sme-smj.t1x.bin sme-smj.autobil.bin

^nom<SN><@SUBJ→><Sg><Nom>{^Wikipedia<N><Prop><Sg><Nom>$}$ ^verb<SV><@+FMAINV>{^liehket<V><Ind><Prs><Sg3>$}$ ^nom<SN><@→N>{^@máŋggagielat<A><Attr>$}$ 
^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>$}$ 
^verb<SV><@+FMAINV>{^liehket<V><Ind><Prs><Sg3>$}$ ^verb<SV><@-FMAINV>{^dahkat<V><Inf>$}$ ^nom<SN><@→N>{^almulasj<A><Attr>$}$ 
^nom<SN><@←OBJ><Sg><Acc>{^@diehtosátnegirji<N><Sg><Acc>$}$ ^adv<Adv>{^ADV><ADV>$}$ ^pronom<SN><@SUBJ→><Sg><Nom>{^guhti<Pron><Rel><Sg><Nom>$}$ 
^adv<Adv>{^beru<ADV>$}$ ^verb<SV>{^sáhttet<V><Ind><Prs><Sg3>$}$ ^verb<SV><@-FMAINV>{^tjállet<V><Inf>$}$ 
^nom<SN><@←OBJ><Pl><Acc>{^artihkal<N><Pl><Acc>$}$.

Running through the whole system
$ echo "Wikipedia lea máŋggagielat prošeakta man ulbmilin lea ráhkadit almmolaš diehtosátnegirjji gosa \
gii beare sáhttá čállit artihkkaliid." | apertium -d . sme-smj

Wikipedia l @máŋggagielat prosjækta man ulmmen l dahkat almulasj @diehtosátnegirji #ADV>  
guhti beru sáhttá tjállet artihkkalijt

See also

External links