In this paper we present a work aimed at testing the most advanced, state-of-the-art syntactic parsers based on deep neural networks (DNN) on Italian. We made a set of experiments by using the Universal Dependencies benchmarks and propose a new solution based on ensemble systems obtaining very good performances.
Parsing Italian texts together is better than parsing them alone! / Antonelli, Oronzo; Tamburini, Fabio. - ELETTRONICO. - 2253:(2018), pp. 27-33. (Intervento presentato al convegno 5th Italian Conference on Computational Linguistics, CLiC-it 2018 tenutosi a Torino nel 2018) [10.4000/books.aaccademia.3063].
Parsing Italian texts together is better than parsing them alone!
Tamburini, Fabio
2018
Abstract
In this paper we present a work aimed at testing the most advanced, state-of-the-art syntactic parsers based on deep neural networks (DNN) on Italian. We made a set of experiments by using the Universal Dependencies benchmarks and propose a new solution based on ensemble systems obtaining very good performances.File in questo prodotto:
Eventuali allegati, non sono esposti
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
