Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.

AHyDA: Automatic Hypernym Detection with feature Augmentation / Pannitto, Ludovica; Salicchi, Lavinia; Lenci, Alessandro. - ELETTRONICO. - (2017), pp. 240-245. (Intervento presentato al convegno Fourth Italian Conference on Computational Linguistics CLiC-it 2017 tenutosi a Roma nel dicembre 2017) [10.4000/books.aaccademia.2437].

AHyDA: Automatic Hypernym Detection with feature Augmentation

Pannitto, Ludovica
Primo
;
2017

Abstract

Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.
2017
Proceedings of the Fourth Italian Conference on Computational Linguistics CLiC-it 2017
240
245
AHyDA: Automatic Hypernym Detection with feature Augmentation / Pannitto, Ludovica; Salicchi, Lavinia; Lenci, Alessandro. - ELETTRONICO. - (2017), pp. 240-245. (Intervento presentato al convegno Fourth Italian Conference on Computational Linguistics CLiC-it 2017 tenutosi a Roma nel dicembre 2017) [10.4000/books.aaccademia.2437].
Pannitto, Ludovica; Salicchi, Lavinia; Lenci, Alessandro
File in questo prodotto:
File Dimensione Formato  
aaccademia-2437.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Creative commons
Dimensione 682.59 kB
Formato Adobe PDF
682.59 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/11585/949659
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact