Lemmatizing KONTATTO!

Our team is now working on the lemmatization of the corpus KONTATTO: a very challenging task, since we are dealing with a complex repertoire including Tyrolean dialect(s), Italian, Trentino and even some Ladin! Lemmas (in standard German, standard Italian and standard Gardenese) are added on a separate line which adds up to the main transcription, and POS and language annotation tiers.

Leave a Reply

Your email address will not be published. Required fields are marked *

*