In this paper, we propose a Deep Learning architecture for several Italian Natural language processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. This architecture provided state of the art performance in several sequence labeling tasks for the English language. We exploit the same approach for the Italian language and extend it for performing a multi-task learning involving PoS-tagging and sentiment analysis. Results show that the system is able to achieve state of the art performance in all the tasks and in some cases overcome the best systems previously developed for the Italian.

Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning

Pierpaolo Basile;Pierluigi Cassotti;Lucia Siciliani;Giovanni Semeraro
2017-01-01

Abstract

In this paper, we propose a Deep Learning architecture for several Italian Natural language processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. This architecture provided state of the art performance in several sequence labeling tasks for the English language. We exploit the same approach for the Italian language and extend it for performing a multi-task learning involving PoS-tagging and sentiment analysis. Results show that the system is able to achieve state of the art performance in all the tasks and in some cases overcome the best systems previously developed for the Italian.
File in questo prodotto:
File Dimensione Formato  
IJCOL 2017 vol 3 BiLSTM CRF Basile.pdf

non disponibili

Tipologia: Documento in Versione Editoriale
Licenza: Creative commons
Dimensione 236.82 kB
Formato Adobe PDF
236.82 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11586/228576
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact