Is it possible to use images to model verb semantic similarities? Starting from this core question, we developed two textual distributionalsemantic models and a visual one. We found it particularly interesting and challenging to investigate this Part of Speech since verbsare not often analysed in researches focused on multimodal distributional semantics. After the creation of the visual and textualdistributional space, the three models were evaluated in relation to SimLex-999, a gold standard resource. Through this evaluation,we demonstrate that, using visual distributional models, it is possible to extract meaningful information and to effectively capture thesemantic similarity between verbs.

Representing Verbs with Visual Argument Vectors

Irene Sucameli
Primo
;
Alessandro Lenci
Secondo
2020-01-01

Abstract

Is it possible to use images to model verb semantic similarities? Starting from this core question, we developed two textual distributionalsemantic models and a visual one. We found it particularly interesting and challenging to investigate this Part of Speech since verbsare not often analysed in researches focused on multimodal distributional semantics. After the creation of the visual and textualdistributional space, the three models were evaluated in relation to SimLex-999, a gold standard resource. Through this evaluation,we demonstrate that, using visual distributional models, it is possible to extract meaningful information and to effectively capture thesemantic similarity between verbs.
2020
979-10-95546-34-4
File in questo prodotto:
File Dimensione Formato  
Sucameli-Lenci-2020-Representing-Verbs-with-Visual-Argument-Vectors-annotated.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Versione finale editoriale
Licenza: Creative commons
Dimensione 245.29 kB
Formato Adobe PDF
245.29 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/11568/1070102
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact