In this paper, we investigate whether aneural network model can learn the mean-ing of natural language quantifiers (no, some and all) from their use in visual con-texts. We show that memory networks per-form well in this task, and that explicit counting is not necessary to the system’s performance, supporting psycholinguistic evidence on the acquisition of quantifiers.

“Look, some green circles!”: Learning to quantify from images / Sorodoc, Ionut; Lazaridou, Angeliki; Boleda Torrent, Gemma; Herbelot, Aurelie Georgette Geraldine; Pezzelle, Sandro; Bernardi, Raffaella. - (2016), pp. 75-79. (Intervento presentato al convegno ACL 2016: 5th Workshop on Vision and Language (VL’16) tenutosi a Berlin, Germany nel 12th August 2016) [10.18653/v1/W16-3211].

“Look, some green circles!”: Learning to quantify from images

Sorodoc Ionut;Lazaridou, Angeliki;Boleda Torrent, Gemma;Herbelot, Aurelie Georgette Geraldine;Pezzelle, Sandro;Bernardi, Raffaella
2016-01-01

Abstract

In this paper, we investigate whether aneural network model can learn the mean-ing of natural language quantifiers (no, some and all) from their use in visual con-texts. We show that memory networks per-form well in this task, and that explicit counting is not necessary to the system’s performance, supporting psycholinguistic evidence on the acquisition of quantifiers.
2016
ACL 2016 5th Workshop on Vision and Language (VL’16): Proceedings of the Workshop
Stroudsburg, PA
Association for Computational Linguistics
978-1-945626-11-1
Sorodoc, Ionut; Lazaridou, Angeliki; Boleda Torrent, Gemma; Herbelot, Aurelie Georgette Geraldine; Pezzelle, Sandro; Bernardi, Raffaella
“Look, some green circles!”: Learning to quantify from images / Sorodoc, Ionut; Lazaridou, Angeliki; Boleda Torrent, Gemma; Herbelot, Aurelie Georgette Geraldine; Pezzelle, Sandro; Bernardi, Raffaella. - (2016), pp. 75-79. (Intervento presentato al convegno ACL 2016: 5th Workshop on Vision and Language (VL’16) tenutosi a Berlin, Germany nel 12th August 2016) [10.18653/v1/W16-3211].
File in questo prodotto:
File Dimensione Formato  
W16-3211.pdf

accesso aperto

Descrizione: Main paper
Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 226.91 kB
Formato Adobe PDF
226.91 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/11572/168591
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact