Plattdüütsch and German/ambiguity resolution
From LING073
Level of Ambiguity
593/443 =1.339.
Ambiguous words corrected
The first ambiguous data that we are working with is German 'Über' which corresponds to 'över' and 'öber'. to separate them we need to change them based on the gender of a preceding noun. with 'över' corresponding with a neuter and öber a masculine or feminine.
<rule>
<match lemma="vor" tags="adj"/> <match lemma="över" tags="n.*"><select lemma="über" tags="pr.*"/></match> </rule>
The next data that we will work with is the determiner 'de' which corresponds to 'die/der' in german, depending on case and gender.
For example: 'de Katt' is 'Die Katze' in German, but 'de Bauer' is 'der Bauer' in German.
<rule>
<match lemma="de" tags="det.*">
<select lemma="die" tags="det.*"/>
</match>
<match tags="n.*.f"/>
</rule>
<rule>
<match lemma="de" tags="det.*">
<select lemma="der" tags="det.*"/>
</match>
<match tags="n.*.m"/>
</rule>