In this paper we explore the possibility to merge the world of Compositional Distributional Semantic Models (CDSM) with Tree Kernels (TK). In particular, we will introduce a specific tree kernel (smoothed tree kernel, or STK) and then show that is possibile to approximate such kernel with the dot product of two vectors obtained compositionally from the sentences, creating in such a way a new CDSM.

Ferrone, L., Zanzotto, F.m. (2014). Distributed Smoothed Tree Kernel. In Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 & the Fourth International Workshop EVALITA 2014 (pp.169-174). Pisa : Pisa University Press [10.12871/CLICIT2014133].

Distributed Smoothed Tree Kernel

ZANZOTTO, FABIO MASSIMO
2014-01-01

Abstract

In this paper we explore the possibility to merge the world of Compositional Distributional Semantic Models (CDSM) with Tree Kernels (TK). In particular, we will introduce a specific tree kernel (smoothed tree kernel, or STK) and then show that is possibile to approximate such kernel with the dot product of two vectors obtained compositionally from the sentences, creating in such a way a new CDSM.
First Italian Conference on Computational Linguistics CLiC-it 2014
Pisa
2014
1
Rilevanza nazionale
contributo
2014
Settore INF/01 - INFORMATICA
Settore ING-INF/05 - SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
English
http://www.fileli.unipi.it/projects/clic/proceedings/vol1/CLICIT2014133.pdf
Intervento a convegno
Ferrone, L., Zanzotto, F.m. (2014). Distributed Smoothed Tree Kernel. In Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 & the Fourth International Workshop EVALITA 2014 (pp.169-174). Pisa : Pisa University Press [10.12871/CLICIT2014133].
Ferrone, L; Zanzotto, Fm
File in questo prodotto:
File Dimensione Formato  
CLICIT2014133.pdf

accesso aperto

Licenza: Copyright dell'editore
Dimensione 303.62 kB
Formato Adobe PDF
303.62 kB Adobe PDF Visualizza/Apri

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/2108/106807
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact