Building a bagpipe with a bag and a pipe: Exploring conceptual combination in vision

S Pezzelle; R Shekhar; Raffaella Bernardi

Back

Building a bagpipe with a bag and a pipe: Exploring conceptual combination in vision

Conference proceeding

Peer reviewed

Building a bagpipe with a bag and a pipe: Exploring conceptual combination in vision

S Pezzelle, R Shekhar and Raffaella Bernardi

Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp.60-64

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/10863/46804

Abstract

This preliminary study investigates whether, and to what extent, conceptual combination is conveyed by vision. Working with noun-noun compounds we show that, for some cases, the composed visual vector built with a simple additive model is effective in approximating the visual vector representing the complex concept. © ACL 2016.All right reserved.

Files and links (1)

url

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85060498067&partnerID=40&md5=e2acbd29de2852daf72c34de0ada6eb0View

Details

Title: Building a bagpipe with a bag and a pipe: Exploring conceptual combination in vision
Creators: S Pezzelle
R Shekhar
Raffaella Bernardi
Publication Details: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp.60-64
ISBN: 9781945626111
Conference: 5th Workshop on Vision and Language, VL 2016 at the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 (Berlin)
Publisher: Association for Computational Linguistics (ACL)
Number of pages: 5
Identifiers: 9781945626111
(UNIBZ)89057430
991007045455301241
Scopus ID: 2-s2.0-85060498067
Academic Unit: Faculty of Computer Science
Language: English
Resource Type: Conference proceeding
Author Names String: Pezzelle S, Shekhar R, Bernardi R
Additional Description: description: Record is part of a bulk validation set

Metrics

1 Record Views