When silver glitters more than gold: Bootstrapping an Italian part-of-speech tagger for Twitter


English. We bootstrap a state-of-the-art part-of-speech tagger to tag Italian Twitter data, in the context of the Evalita 2016 PoSTWITA shared task. We show that training the tagger on native Twitter data enriched with little amounts of specifically selected gold data and additional silver-labelled data scraped from Facebook, yields better results than… (More)


6 Figures and Tables

Slides referencing similar topics