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

Boleda, Gemma; Sorodoc, Ionut-Teodor; Lazaridou, Angeliki; Herbelot, Aurélie; Pezzelle, Sandro; Bernardi, Raffaella

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

Llicència

Citació

Sorodoc I, Lazaridou A, Boleda A, Herbelot A, Pezzelle S, Bernardi R. “Look, some green circles!”: learning to quantify from images. In: Proceedings of the 5th Workshop on Vision and Language (ACL 2016). Berlin: Association for Computational Linguistics; 2016. p. 75-79.

Resum

In this paper, we investigate whether a neural network model can learn the meaning of natural language quantifiers (no,some and all) from their use in visual contexts. We show that memory networks perform well in this task, and that explicit counting is not necessary to the system’s performance, supporting psycholinguistic evidence on the acquisition of quantifiers.