Logo image
Back
"look, some green circles!": Learning to quantify from images
Conference proceeding   Peer reviewed

"look, some green circles!": Learning to quantify from images

I Sorodoc, A Lazaridou, G Boleda, A Herbelot, S Pezzelle and Raffaella Bernardi
Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp.75-79
5th Workshop on Vision and Language, VL 2016 at the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 (Berlin)
2016
Handle:
https://hdl.handle.net/10863/46806

Abstract

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. © ACL 2016.All right reserved.
url
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121299627&partnerID=40&md5=4a68e3e386c2468de067f934f2efabc8View

Details

Metrics

1 Record Views
Logo image