Weighting with the bilingual dictionary

From Apertium
Revision as of 22:49, 22 May 2020 by Khannatanmai (talk | contribs)
Jump to navigation Jump to search
$ cat bidix.dix 
<dictionary>
<alphabet>abcdefghijklmnopqrstuvwxyz</alphabet>
<sdefs>
<sdef n="n"/>
<sdef n="vblex"/>
<sdef n="inf"/>
<sdef n="sg"/>
<sdef n="pl"/>
</sdefs>
<section id="main" type="standard">
<e><p><l>cat<s n="n"/></l><r>gato<s n="n"/></r></p></e>
<e><p><l>bat<s n="n"/></l><r>murciélago<s n="n"/></r></p></e>
<e><p><l>rat<s n="vblex"/></l><r>delatar<s n="vblex"/></r></p></e>
</section>
</dictionary>


$ cat analyser.dix 
<dictionary>
<alphabet/>
<sdefs>
<sdef n="n"/>
<sdef n="vblex"/>
<sdef n="ger"/>
<sdef n="inf"/>
<sdef n="pres"/>
<sdef n="sg"/>
<sdef n="pl"/>
</sdefs>
<pardefs>
  <pardef n="cat__n">
    <e><p><l></l><r><s n="n"/><s n="sg"/></r></p></e>
    <e><p><l>s</l><r><s n="n"/><s n="pl"/></r></p></e>
  </pardef>
  <pardef n="pat__vblex">
    <e><p><l></l><r><s n="vblex"/><s n="inf"/></r></p></e>
    <e><p><l>s</l><r><s n="vblex"/><s n="pres"/></r></p></e>
    <e><p><l>ting</l><r><s n="vblex"/><s n="ger"/></r></p></e>
  </pardef>
</pardefs>
<section id="main" type="standard">
<e lm="cat"><i>cat</i><par n="cat__n"/></e>
<e lm="rat"><i>rat</i><par n="cat__n"/></e>
<e lm="bat"><i>bat</i><par n="cat__n"/></e>
<e lm="pat"><i>pat</i><par n="cat__n"/></e>
<e lm="cat"><i>cat</i><par n="pat__vblex"/></e>
<e lm="rat"><i>rat</i><par n="pat__vblex"/></e>
<e lm="bat"><i>bat</i><par n="pat__vblex"/></e>
<e lm="pat"><i>pat</i><par n="pat__vblex"/></e>
</section>
</dictionary>

all:
	lt-comp lr bidix.dix bidix.bin
	lt-print bidix.bin > bidix.att
	hfst-txt2fst -e ε bidix.att -o bidix.hfst
	echo "?*" | hfst-regexp2fst -o anystar.hfst
	hfst-concatenate -1 bidix.hfst -2 anystar.hfst -o bidix-prefixes.hfst
	lt-comp lr analyser.dix analyser.bin
	lt-print analyser.bin > analyser.att
	hfst-txt2fst -e ε analyser.att -o analyser.hfst
	hfst-compose -1 analyser.hfst -2 bidix-prefixes.hfst -o analyser-bidix-found.hfst
	hfst-project -p input analyser-bidix-found.hfst -o analyser-found.analyses.hfst
	hfst-invert analyser.hfst | hfst-compose -1 - -2 analyser-found.analyses.hfst | hfst-invert -o analyser-found.hfst
	hfst-subtract -1 analyser.hfst -2 analyser-found.hfst -o analyser-unfound.hfst
	hfst-reweight -a 1 analyser-unfound.hfst -o analyser-unfound.weighted.hfst
	hfst-union -1 analyser-unfound.weighted.hfst -2 analyser-found.hfst -o analyser.weighted.hfst
	hfst-fst2txt analyser.weighted.hfst -o analyser.weighted.att
	lt-comp lr analyser.weighted.att analyser.weighted.bin

clean:	
	rm *.hfst *.att

$ hfst-fst2strings -w analyser.weighted.hfst
pat:pat<vblex><inf>	6
pats:pat<vblex><pres>	6
patting:pat<vblex><ger>	8
pat:pat<n><sg>	6
pats:pat<n><pl>	6
batting:bat<vblex><ger>	8
catting:cat<vblex><ger>	8
cat:cat<n><sg>	0
cat:cat<vblex><inf>	0
cats:cat<n><pl>	0
cats:cat<vblex><pres>	0
rat:rat<n><sg>	0
rat:rat<vblex><inf>	0
ratting:rat<vblex><ger>	0
rats:rat<n><pl>	0
rats:rat<vblex><pres>	0
bat:bat<n><sg>	0
bat:bat<vblex><inf>	0
bats:bat<n><pl>	0
bats:bat<vblex><pres>	0

Solution using lt-trim

all:
        lt-comp lr analyser.dix analyser.bin
        lt-comp lr bidix.dix bidix.bin
        lt-trim analyser.bin bidix.bin analyser-found.bin
        lt-print analyser.bin > analyser.att
        lt-print analyser-found.bin > analyser-found.att
        hfst-txt2fst -e ε analyser.att -o analyser.hfst
        hfst-txt2fst -e ε analyser-found.att -o analyser-found.hfst
 
        hfst-subtract -1 analyser.hfst -2 analyser-found.hfst -o analyser-unfound.hfst
        hfst-reweight -a 1 analyser-unfound.hfst -o analyser-unfound.weighted.hfst
        hfst-union -1 analyser-unfound.weighted.hfst -2 analyser-found.hfst -o analyser.weighted.hfst
        hfst-fst2txt analyser.weighted.hfst -o analyser.weighted.att
        lt-comp lr analyser.weighted.att analyser.weighted.bin
clean:
        rm *.hfst *.att

Output

pat:pat<vblex><inf>	6
pats:pat<vblex><pres>	6
patting:pat<vblex><ger>	8
pat:pat<n><sg>	6
pats:pat<n><pl>	6
bat:bat<vblex><inf>	6
bats:bat<vblex><pres>	6
batting:bat<vblex><ger>	8
rat:rat<n><sg>	6
rats:rat<n><pl>	6
cat:cat<vblex><inf>	6
cats:cat<vblex><pres>	6
catting:cat<vblex><ger>	8
cat:cat<n><sg>	0
cats:cat<n><pl>	0
rat:rat<vblex><inf>	0
rats:rat<vblex><pres>	0
ratting:rat<vblex><ger>	0
bat:bat<n><sg>	0
bats:bat<n><pl>	0