Combining Geometric, Textual and Visual Features for Predicting Prepositions in Image Descriptions

Ramisa, A., Wang, J.K. orcid.org/0000-0003-0048-3893, Lu, Y. et al. (3 more authors) (2015) Combining Geometric, Textual and Visual Features for Predicting Prepositions in Image Descriptions. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing, 17-21 Sep 2015, Lisbon, Portugal. Association for Computational Linguistics , pp. 214-220.

Abstract

We investigate the role that geometric, textual and visual features play in the task of predicting a preposition that links two visual entities depicted in an image. The task is an important part of the subsequent process of generating image descriptions. We explore the prediction of prepositions for a pair of entities, both in the case when the labels of such entities are known and unknown. In all situations we found clear evidence that all three features contribute to the prediction task.

Metadata

Item Type:	Proceedings Paper
Authors/Creators:	Ramisa, A. Wang, J.K. https://orcid.org/0000-0003-0048-3893 Lu, Y. Dellandrea, E. Moreno-Noguer, F. Gaizauskas, R. https://orcid.org/0000-0002-3356-5126
Copyright, Publisher and Additional Information:	© 2015 Association for Computational Linguistics. This is an author produced version of a paper subsequently published in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Uploaded in accordance with the publisher's self-archiving policy.
Dates:	Published: 19 September 2015 Accepted: 29 July 2015
Institution:	The University of Sheffield
Academic Units:	The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield)
Funding Information:	Funder Grant number ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL (EPSRC) EP/K019082/1
Depositing User:	Symplectic Sheffield
Date Deposited:	19 May 2016 08:07
Last Modified:	11 Apr 2017 21:53
Published Version:	http://aclweb.org/anthology/D15-1022
Status:	Published
Publisher:	Association for Computational Linguistics
Refereed:	Yes
Open Archives Initiative ID (OAI ID):	oai:eprints.whiterose.ac.uk:99022

CORE (COnnecting REpositories)

Combining Geometric, Textual and Visual Features for Predicting Prepositions in Image Descriptions

Abstract

Metadata

Download

Accepted Version

Export

Statistics