Deal with wrong normalizations

[pfefferniels]

While generally text normalization using DTA's CAB service works fine, it introduces some mistakes, e.g. Schleiffer gets normalized to "Schluffer" and some more. Probably we should collect those and correct them after normalization again.

[pfefferniels]

further mistakes

• PS 20: Palmulen => Palmölen (it's seems to be possible to restrict the rewrite model to the 18th century, which maybe makes this choice less likely?)
• PS 20: Lambertischen => Lombertischen
• PS 20: the quote by St. Lambert is correctly recognized as French, but still wrongly normalized (for the word "on" it results in <w id="w2a2" t="on" b="4849 2"><xlit isLatinExt="1" isLatin1="1" latin1Text="on"/><moot tag="FM.fr" word="ohne" lemma="ohne"/>on</w>)
• PS 1: Zieffern => Ziefern
• passim: somewhat problematic is the transcription of "Clavier" als "Klavier".
• PS 24: Auszierungen => Aussierungen
• PS 19: an Statt => an Stadt

[pfefferniels]

Not sure if relevant, but CAB seems to make use of an "exception lexicon"

[rettinghaus]

Could we report those errors for improving the language model?

[pfefferniels]

Yes absolutely – I'd suggest to collect as many as possible and report them in one go. Not sure where exactly to report though … (Bryan Jurish perhaps?)